diff --git "a/papers.csv" "b/papers.csv" --- "a/papers.csv" +++ "b/papers.csv" @@ -25,14 +25,14 @@ Practical and Scalable Desktop-based High-Quality Facial Capture,Alexandros Latt Tracking Objects as Pixel-wise Distributions,Zelin Zhao (The Chinese University of Hong Kong)*; Ze Wu (Megvii); Yueqing Zhuang (Megvii Inc Company); Boxun Li (Megvii Inc.); Jiaya Jia (Chinese University of Hong Kong),,,Oral,http://arxiv.org/abs/2207.05518,,,, CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation,"Yunyao Mao (University of Science and Technology of China)*; Wengang Zhou (University of Science and Technology of China); Zhenbo Lu (Institute of Artificial Intelligence, Hefei Comprehensive National Science Center); Jiajun Deng (University of Science and Technology of China); Houqiang Li (University of Science and Technology of China)",,,Oral,http://arxiv.org/abs/2208.12448,https://github.com/maoyunyao/CMD,,, Open-Vocabulary DETR with Conditional Matching,Yuhang Zang (Nanyang Technological University)*; Wei Li (Nanyang Technological University); Kaiyang Zhou (Nanyang Technological University); Chen Huang (Apple); Chen Change Loy (Nanyang Technological University),,,Oral,http://arxiv.org/abs/2203.11876,,,, -Towards Calibrated Hyper-sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning,"Hualiang Wang (Zhejiang University)*; Siming FU (Zhejiang University); Xiaoxuan He (Zhejiang University); Hangxiang Fang (Zhejiang University); Zuozhu Liu (Zhejiang-UIUC Institute); Haoji Hu (Zhejiang University, China)",,,Oral,http://arxiv.org/abs/2208.10043,https://github.com/VipaiLab/vMF\_OP,,, +Towards Calibrated Hyper-sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning,"Hualiang Wang (Zhejiang University)*; Siming FU (Zhejiang University); Xiaoxuan He (Zhejiang University); Hangxiang Fang (Zhejiang University); Zuozhu Liu (Zhejiang-UIUC Institute); Haoji Hu (Zhejiang University, China)",,,Oral,http://arxiv.org/abs/2208.10043,https://github.com/VipaiLab/vMF_OP,,, FBNet: Feedback Network for Point Cloud Completion,Xuejun Yan (Hikvision Research Institue)*; Hongyu Yan (Sichuan Universite); Jingjing Wang (Hikvision Research Institute); Hang Du (Hikvision Research Institute); Zhihong Wu (Sichuan University); Di Xie (Hikvision Research Institute); Shiliang Pu (Hikvision Research Institute); Li Lu (Sichuan University),,,Oral,,,,, Physically-Based Editing of Indoor Scene Lighting from a Single Image,Zhengqin Li (Meta)*; Jia Shi (Carnegie Mellon University); Sai Bi (Adobe Research); Rui Zhu (University of California San Diego ); Kalyan Sunkavalli (Adobe Research); Milos Hasan (Adobe Research); Zexiang Xu (Adobe Research); Ravi Ramamoorthi (University of California San Diego); Manmohan Chandraker (UC San Diego),,,Oral,http://arxiv.org/abs/2205.09343,,,, GLASS: Global to Local Attention for Scene-Text Spotting,Roi Ronen (Technion)*; Shahar Tsiper (Amazon); Oron Anschel (AWS); Inbal Lavi (Amazon); Amir Markovitz (Amazon); R. Manmatha (Amazon),,,Oral,http://arxiv.org/abs/2208.03364,,,, -Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation,Antonin Vobecky (Czech Technical University in Prague)*; David Hurych (Valeo.ai); Oriane Siméoni (valeo.ai); Spyros Gidaris (valeo.ai); Andrei Bursuc (valeo.ai); Patrick Pérez (Valeo.ai); Josef Sivic (Czech Technical University),,,Oral,,,,, +Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation,Antonin Vobecky (Czech Technical University in Prague)*; David Hurych (Valeo.ai); Oriane Siméoni (valeo.ai); Spyros Gidaris (valeo.ai); Andrei Bursuc (valeo.ai); Patrick Pérez (Valeo.ai); Josef Sivic (Czech Technical University),,,Oral,,,,, Expanding Language-Image Pretrained Models for General Video Recognition,"Bolin Ni (Institute of Automation, Chinese Academy of Sciences); Houwen Peng (Microsoft Research)*; Minghao Chen (Stony Brook University); Songyang Zhang (University of Rochester); Gaofeng Meng (Chinese Academy of Sciences); Jianlong Fu (Microsoft Research); SHIMING XIANG (Chinese Academy of Sciences, China); Haibin Ling (Stony Brook University)",,,Oral,http://arxiv.org/abs/2208.02816,,,, -Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes,"Julian Chibane (Max Planck Institute for Informatics, University of Wuerzburg)*; Francis Engelmann (ETH AI Center); Anh Tuan Tran (Max Planck Institute for Informatics, Saarland University); Gerard Pons-Moll (University of Tübingen)",,,Oral,http://arxiv.org/abs/2206.01203,,,, -Pose-NDF: Modelling Human Pose Manifolds with Neural Distance Fields,"Garvita Tiwari (MPI-INF, University of Tübingen)*; Dimitrije Antic (University of Tuebingen); Jan E. Lenssen (TU Dortmund); Nikolaos Sarafianos (Facebook Reality Labs); Tony Tung (Facebook Reality Labs); Gerard Pons-Moll (University of Tübingen)",,,Oral,,,,, +Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes,"Julian Chibane (Max Planck Institute for Informatics, University of Wuerzburg)*; Francis Engelmann (ETH AI Center); Anh Tuan Tran (Max Planck Institute for Informatics, Saarland University); Gerard Pons-Moll (University of Tübingen)",,,Oral,http://arxiv.org/abs/2206.01203,,,, +Pose-NDF: Modelling Human Pose Manifolds with Neural Distance Fields,"Garvita Tiwari (MPI-INF, University of Tübingen)*; Dimitrije Antic (University of Tuebingen); Jan E. Lenssen (TU Dortmund); Nikolaos Sarafianos (Facebook Reality Labs); Tony Tung (Facebook Reality Labs); Gerard Pons-Moll (University of Tübingen)",,,Oral,,,,, Multimodal Object Detection via Probabilistic Ensembling,Yi-Ting Chen (University of Maryland); Jinghao Shi (Carnegie Mellon University); Zelin Ye (CMU); Mertz Christoph (CMU); Deva Ramanan (Carnegie Mellon University); Shu Kong (Carnegie Mellon University)*,,,Oral,http://arxiv.org/abs/2104.02904,,,, CenterFormer: Center-based Transformer for 3D Object Detection,"Zixiang Zhou (University of Central Florida)*; xiangchen zhao (Tusimple); Yu Wang (Tusimple); Panqu Wang (TuSimple, Inc); Hassan Foroosh (University of Central Florida)",,,Oral,,,,, Revisiting a kNN-based Image Classification System with High-capacity Storage,Kengo Nakata (Kioxia Corporation)*; Youyang Ng (Kioxia Corporation); Daisuke Miyashita (Kioxia Corporation); Asuka Maki (Kioxia Corporation); Yu-Chieh Lin (Kioxia Corporation); Jun Deguchi (Kioxia Corporation),,,Oral,http://arxiv.org/abs/2204.01186,,,, @@ -44,18 +44,17 @@ Registration based Few-Shot Anomaly Detection,"Chaoqin Huang (Shanghai Jiao Tong A Level Set Theory for Neural Implicit Evolution under Explicit Flows,Ishit Mehta (University of California San Diego)*; Manmohan Chandraker (UC San Diego); Ravi Ramamoorthi (University of California San Diego),,,Oral,http://arxiv.org/abs/2204.07159,,,, Improving Robustness by Enhancing Weak Subnets,Yong Guo (Max Planck Institute for Informatics)*; David Stutz (Max Planck Institute for Informatics); Bernt Schiele (MPI Informatics),,,Oral,http://arxiv.org/abs/2201.12765,,,, TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes,"Mutian Xu (The Chinese University of Hong Kong (Shenzhen))*; Pei Chen (the Chinese University of Hong Kong (Shenzhen)); Haolin Liu (The Chinese University of Hong Kong, Shenzhen); Xiaoguang Han (Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong (Shenzhen))",,,Oral,,,,, -PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark,"Li Chen (Shanghai AI Laboratory)*; Chonghao Sima (Purdue University); Yang Li (SenseTime); Zehan Zheng (Shanghai AI Laboratory); Jiajie Xu (Carnegie Mellon University); Xiangwei Geng (SenseTime); Hongyang Li (SenseTime); Conghui He (Shanghai AI Lab); Jianping Shi (Sensetime Group Limited); Yu Qiao (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences); Junchi Yan (Shanghai Jiao Tong University)",,,Oral,http://arxiv.org/abs/2203.11089,"https://github.com/OpenPerceptionX/PersFormer_3DLane and OpenLane dataset is -provided at https://github.com/OpenPerceptionX/OpenLane",,, +PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark,"Li Chen (Shanghai AI Laboratory)*; Chonghao Sima (Purdue University); Yang Li (SenseTime); Zehan Zheng (Shanghai AI Laboratory); Jiajie Xu (Carnegie Mellon University); Xiangwei Geng (SenseTime); Hongyang Li (SenseTime); Conghui He (Shanghai AI Lab); Jianping Shi (Sensetime Group Limited); Yu Qiao (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences); Junchi Yan (Shanghai Jiao Tong University)",,,Oral,http://arxiv.org/abs/2203.11089,https://github.com/OpenPerceptionX/PersFormer_3DLane,,, Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting,Chuhui Xue (Nanyang Technological University); Wenqing Zhang (ByteDance); Yu Hao (Bytedance Inc.); Shijian Lu (Nanyang Technological University); Philip Torr (University of Oxford); Song Bai (University of Oxford)*,,,Oral,http://arxiv.org/abs/2203.03911,,,, Adaptive Patch Exiting for Scalable Single Image Super-Resolution,Shizun Wang (Beijing University of Posts and Telecommunications)*; Jiaming Liu (Peking University); Kaixin Chen (Beijing University of Posts and Telecommunications); Xiaoqi Li (Columbia university in the city of New york); Ming Lu (Intel Labs China); Yandong Guo (OPPO Research Institute),,,Oral,http://arxiv.org/abs/2203.11589,https://github.com/littlepure2333/APE,,, Perceptual Artifacts Localization for Inpainting,"Lingzhi Zhang (University of Pennsylvania)*; Yuqian Zhou (Adobe); Connelly Barnes (Adobe); Zhe Lin (Adobe Research); Eli Shechtman (Adobe Research, US); Sohrab Amirghodsi (Adobe Research); Jianbo Shi (University of Pennsylvania)",,,Oral,http://arxiv.org/abs/2208.03357,,,, Adversarially-Aware Robust Object Detector,ZiYi Dong (Sun Yat-Sen University)*; Pengxu Wei (Sun Yat-sen University); Liang Lin (Sun Yat-sen University),,,Oral,http://arxiv.org/abs/2207.06202,,,, RFNet-4D: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds,"Tuan-Anh Vu (The Hong Kong University of Science and Technology)*; Thanh Nguyen (Deakin University, Australia); Binh-Son Hua (VinAI Research); Quang Hieu Pham (Woven Planet North America); Sai-Kit Yeung (Hong Kong University of Science and Technology)",,,Oral,,,,, Generalizable Patch-Based Neural Rendering,Mohammed Suhail (University of British Columbia)*; Carlos Esteves (Google Research); Leonid Sigal (University of British Columbia); Ameesh Makadia (Google Research),,,Oral,http://arxiv.org/abs/2207.10662,,,, -A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow,Jenny Schmalfuss (University of Stuttgart)*; Philipp Scholze (University of Stuttgart); Andrés Bruhn (University of Stuttgart),,,Oral,http://arxiv.org/abs/2203.13214,https://github.com/cv-stuttgart/PCFA,,, +A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow,Jenny Schmalfuss (University of Stuttgart)*; Philipp Scholze (University of Stuttgart); Andrés Bruhn (University of Stuttgart),,,Oral,http://arxiv.org/abs/2203.13214,https://github.com/cv-stuttgart/PCFA,,, Contrastive Monotonic Pixel-Level Modulation,Kun Lu (Zhejiang University)*; Rongpeng Li (Zhejiang University); Honggang Zhang (Zhejiang University),,,Oral,http://arxiv.org/abs/2207.11517,https://github.com/lukun199/MonoPix,,, Social-SSL: Self-Supervised Cross-Sequence Representation Learning Based on Transformers for Multi-Agent Trajectory Prediction,Li-Wu Tsao (National Chiao Tung University)*; Yan-Kai Wang (National Chiao Tung University); Hao-Siang Lin (National Chiao Tung University); Hong-Han Shuai (National Yang Ming Chiao Tung University); Lai-Kuan Wong (Multimedia University); Wen-Huang Cheng (National Chiao Tung University),,,Oral,,,,, -SpOT: Spatiotemporal Modeling for 3D Object Tracking,Colton Stearns (Stanford University)*; Davis Rempe (Stanford University); Jie Li (Toyota Research Institute); Rareș A Ambruș (Toyota Research Institute); Sergey Zakharov (Toyota Research Institute); Vitor Guizilini (Toyota Research Institute); Yanchao Yang (Stanford University); Leonidas Guibas (Stanford University),,,Oral,http://arxiv.org/abs/2207.05856,,,, +SpOT: Spatiotemporal Modeling for 3D Object Tracking,Colton Stearns (Stanford University)*; Davis Rempe (Stanford University); Jie Li (Toyota Research Institute); RareÈ™ A AmbruÈ™ (Toyota Research Institute); Sergey Zakharov (Toyota Research Institute); Vitor Guizilini (Toyota Research Institute); Yanchao Yang (Stanford University); Leonidas Guibas (Stanford University),,,Oral,http://arxiv.org/abs/2207.05856,,,, Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition,Xudong Xie (Huazhong University of Science and Technology)*; LING FU (Huazhong University of Science and Technology); Zhifei Zhang (Adobe Research); Zhaowen Wang (Adobe Research); Xiang Bai (Huazhong University of Science and Technology),,,Oral,http://arxiv.org/abs/2208.00438,,,, Monocular 3D Object Detection with Depth from Motion,Tai Wang (The Chinese University of Hong Kong)*; Jiangmiao Pang (CUHK); Dahua Lin (The Chinese University of Hong Kong),,,Oral,http://arxiv.org/abs/2207.12988,https://github.com/Tai-Wang/Depth-from-Motion,,, Fine-Grained Scene Graph Generation with Data Transfer,Ao Zhang (National University of Singapore)*; Yuan Yao (Tsinghua University); qianyu chen (Tsinghua University); Wei Ji (National University of Singapore); Zhiyuan Liu (Tsinghua University); Maosong Sun (Tsinghua University); Tat-Seng Chua (National university of Singapore),,,Oral,http://arxiv.org/abs/2203.11654,https://github.com/waxnkw/IETrans-SGG.pytorch,,, @@ -91,8 +90,8 @@ Perceiving and Modeling Density for Image Dehazing,Tian Ye (Jimei University)*; ROBIN: A Benchmark for Robustness to Individual Nuisances in Real-World Out-of-Distribution Shifts,Bingchen Zhao (University of Edinburgh)*; Shaozuo Yu (Tongji University); Wufei Ma (Purdue University); Mingxin Yu (Peking University); Shenxiao Mei (Johns Hopkins University); Angtian Wang (Johns Hopkins University); Ju He (Johns Hopkins University); Alan Yuille (Johns Hopkins University); Adam Kortylewski (Max Planck Institute for Informatics),,,Oral,,,,, Delving into Details: Synopsis-to-Detail Networks for Video Recognition,Shuxian Liang (Zhejiang University)*; Xu Shen (Alibaba Group); Jianqiang Huang (Alibaba Group); Xian-Sheng Hua (Alibaba Group),,,Oral,,,,, Bringing Rolling Shutter Images Alive with Dual Reversed Distortion,Zhihang Zhong (The University of Tokyo); Mingdeng Cao (Tsinghua University); Xiao Sun (Microsoft Research Asia); Zhirong Wu (Microsoft Research); Zhongyi Zhou (The University of Tokyo); Yinqiang Zheng (The University of Tokyo)*; Stephen Lin (Microsoft Research); Imari Sato (National Institute of Informatics),,,Oral,http://arxiv.org/abs/2203.06451,https://github.com/zzh-tech/Dual-Reversed-RS,,, -SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation,Yanjie Li (Tsinghua University)*; Sen Yang (Southeast University); Peidong Liu (Tsinghua University); 寿奎 张 (meituan); Yunxiao Wang (Tsinghua University); Zhicheng Wang (Nreal); Wankou Yang (Southeast University); Shu-Tao Xia (Tsinghua University),,,Oral,http://arxiv.org/abs/2107.03332,,,, -Generative Multiplane Images: Making a 2D GAN 3D-Aware,Xiaoming Zhao (University of Illinois at Urbana-Champaign)*; Fangchang Ma (Apple Inc.); David Güera (Apple Inc.); Zhile Ren (Apple Inc.); Alexander Schwing (UIUC); Alex Colburn (Apple Inc.),,,Oral,http://arxiv.org/abs/2207.10642,,,, +SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation,Yanjie Li (Tsinghua University)*; Sen Yang (Southeast University); Peidong Liu (Tsinghua University); 寿奎 å¼  (meituan); Yunxiao Wang (Tsinghua University); Zhicheng Wang (Nreal); Wankou Yang (Southeast University); Shu-Tao Xia (Tsinghua University),,,Oral,http://arxiv.org/abs/2107.03332,,,, +Generative Multiplane Images: Making a 2D GAN 3D-Aware,Xiaoming Zhao (University of Illinois at Urbana-Champaign)*; Fangchang Ma (Apple Inc.); David Güera (Apple Inc.); Zhile Ren (Apple Inc.); Alexander Schwing (UIUC); Alex Colburn (Apple Inc.),,,Oral,http://arxiv.org/abs/2207.10642,,,, Self-supervised Social Relation Representation for Human Group Detection,"Jiacheng Li (College of Intelligence and Computing, Tianjin University); Ruize Han (College of Intelligence and Computing, Tianjin University)*; Haomin Yan (Tianjin University); Zekun Qian (College of Intelligence and Computing, Tianjin University); Wei Feng (College of Intelligence and Computing, Tianjin University, China); Song Wang (University of South Carolina)",,,Oral,http://arxiv.org/abs/2203.03843,,,, Stripformer: Strip Transformer for Fast Image Deblurring,Fu-Jen Tsai (National Tsing Hua University)*; Yan-Tsung Peng (National Chengchi University); Yen-Yu Lin (National Yang Ming Chiao Tung University); Chung-Chi Tsai (Qualcomm Technology); Chia-Wen Lin (National Tsing Hua University),,,Oral,http://arxiv.org/abs/2204.04627,,,, Deep Fourier-based Exposure Correction Network with Spatial-Frequency Interaction,Jie Huang (University of Science and Technology of China); Yajing Liu (USTC); Feng Zhao (University of Science and Technology of China)*; Keyu Yan (University of Science and Technology of China); Jinghao Zhang (University of Science and Technology of China); Yukun Huang (University of Science and Technology of China); man zhou (University of Science and Technology of China); Zhiwei Xiong (University of Science and Technology of China),,,Oral,,,,, @@ -102,11 +101,11 @@ Semantic-Aware Fine-Grained Correspondence,Yingdong Hu (Tsinghua University); Re Layered Controllable Video Generation,Jiahui Huang (University of British Columbia)*; Yuhe Jin (University of British Columbia); Kwang Moo Yi (University of British Columbia); Leonid Sigal (University of British Columbia),,,Oral,http://arxiv.org/abs/2111.12747,,,, GraphVid: It Only Takes a Few Nodes to Understand a Video,Eitan Kosman (Bosch AI)*; Dotan Di Castro (Bosch),,,Oral,http://arxiv.org/abs/2207.01375,,,, Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection,Yu Hong (Zhejiang University); Hang Dai (Mohamed bin Zayed University of Artificial Intelligence)*; Yong Ding (Zhejiang University),,,Oral,,,,, -Adaptive Token Sampling For Efficient Vision Transformers,Mohsen Fayyaz (Microsoft)*; Soroush Abbasi Koohpayegani (University of Maryland Baltimore County); Farnoush Rezaei Jafari (Technische Universität Berlin); Sunando Sengupta (Microsoft); HAMID VAEZI JOZE (Microsoft); Eric Sommerlade (Microsoft); Hamed Pirsiavash (University of California Davis); Jürgen Gall (University of Bonn),,,Oral,http://arxiv.org/abs/2111.15667,,,, -Implicit Field Supervision For Robust Non-Rigid Shape Matching,Ramana S Sundararaman (Ecole Polytechnique)*; Gautam Pai (École Polytechnique); Maks Ovsjanikov (Ecole polytechnique),,,Oral,http://arxiv.org/abs/2203.07694,,,, +Adaptive Token Sampling For Efficient Vision Transformers,Mohsen Fayyaz (Microsoft)*; Soroush Abbasi Koohpayegani (University of Maryland Baltimore County); Farnoush Rezaei Jafari (Technische Universität Berlin); Sunando Sengupta (Microsoft); HAMID VAEZI JOZE (Microsoft); Eric Sommerlade (Microsoft); Hamed Pirsiavash (University of California Davis); Jürgen Gall (University of Bonn),,,Oral,http://arxiv.org/abs/2111.15667,,,, +Implicit Field Supervision For Robust Non-Rigid Shape Matching,Ramana S Sundararaman (Ecole Polytechnique)*; Gautam Pai (École Polytechnique); Maks Ovsjanikov (Ecole polytechnique),,,Oral,http://arxiv.org/abs/2203.07694,,,, NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing,Bangbang Yang (Zhejiang University); Chong Bao (Zhejiang University); Junyi Zeng (Zhejiang University); Hujun Bao (Zhejiang University); Yinda Zhang (Google); Zhaopeng Cui (Zhejiang University); Guofeng Zhang (Zhejiang University)*,,,Oral,http://arxiv.org/abs/2207.11911,,,, KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution,"Jiahong Fu (Xi'an Jiaotong University)*; Hong Wang (Jarvis Lab,Tencent ); Qi Xie (Xi'an Jiaotong University); Qian Zhao (Xi'an Jiaotong University); Deyu Meng (Xi'an Jiaotong University); Zongben Xu (Xi'an Jiaotong University)",,,Oral,,,,, -RealFlow: EM-based Realistic Optical Flow Datasets Generation from Videos,"Yunhui Han (THU;Megvii); Kunming Luo (Megvii); Ao Luo (Megvii); Jiangyu Liu (megvii inc); Haoqiang Fan (Megvii Inc（face++）); Guiming Luo (School of Software, Tsinghua University); Shuaicheng Liu (UESTC; Megvii)*",,,Oral,,https://github.com/megvii-research/RealFlow,,, +RealFlow: EM-based Realistic Optical Flow Datasets Generation from Videos,"Yunhui Han (THU;Megvii); Kunming Luo (Megvii); Ao Luo (Megvii); Jiangyu Liu (megvii inc); Haoqiang Fan (Megvii Inc（face++）); Guiming Luo (School of Software, Tsinghua University); Shuaicheng Liu (UESTC; Megvii)*",,,Oral,,https://github.com/megvii-research/RealFlow,,, Semi-supervised Object Detection via Virtual Category Learning,"Changrui Chen (University of Warwick); Kurt Debattista (University of Warwick, UK); Jungong Han (Aberystwyth University)*",,,Oral,http://arxiv.org/abs/2207.03433,,,, PrivHAR: Recognizing Human Actions From Privacy-preserving Lens,Carlos Hinojosa (Universidad Industrial de Santander)*; Miguel A Marquez (UIS Colombia); Henry Arguello (Universidad Industrial Santander); Ehsan Adeli (Stanford University); Li Fei-Fei (Stanford University); Juan Carlos Niebles (Salesforce & Stanford University),,,Oral,http://arxiv.org/abs/2206.03891,,,, Solution Space Analysis of Essential Matrix based on Algebraic Error Minimization,Gaku Nakano (NEC Corporation)*,,,Oral,,,,, @@ -121,13 +120,13 @@ Sim-2-Sim Transfer for Vision-and-Language Navigation in Continuous Environments Uncertainty-DTW for Time Series and Sequences,Lei Wang (The Australian National University); Piotr Koniusz (ANU College of Engineering and Computer Science)*,,,Oral,,,,, Affine Correspondences between Multi-Camera Systems for 6DOF Relative Pose Estimation,Banglei Guan (National University of Defense Technology)*; Ji Zhao (Huazhong University of Science and Technology),,,Oral,,,,, Improving Self-supervised Lightweight Model Learning via Hard-aware Metric Distillation,Hao Liu (Beijing Institute of Technology); Mang Ye (Wuhan University)*,,,Oral,,,,, -NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion,"Chenfei Wu (Microsoft)*; Jian Liang (Peking University); Lei Ji (Microsoft); Fan Yang (MSRA); Yuejian Fang (Peking University); Daxin Jiang (Microsoft, Beijing, China); Nan Duan (Microsoft Research)",,,Oral,,,,, +NÃœWA: Visual Synthesis Pre-training for Neural visUal World creAtion,"Chenfei Wu (Microsoft)*; Jian Liang (Peking University); Lei Ji (Microsoft); Fan Yang (MSRA); Yuejian Fang (Peking University); Daxin Jiang (Microsoft, Beijing, China); Nan Duan (Microsoft Research)",,,Oral,,,,, BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation,Ye Yu (Microsoft)*; Jialin Yuan (Oregon State University); Gaurav Mittal (Microsoft); Li Fuxin (Oregon State University); Mei Chen (Microsoft),,,Oral,http://arxiv.org/abs/2208.01159,,,, DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras,Ruizhi Shao (Tsinghua University); Zerong Zheng (Tsinghua University); Hongwen Zhang (Tsinghua University); Jingxiang Sun (University of Illinois Urbana-Champaign); Yebin Liu (Tsinghua University)*,,,Oral,http://arxiv.org/abs/2207.08000,,,, The Challenges of Continuous Self-Supervised Learning,Senthil Purushwalkam (Carnegie Mellon University); Pedro Morgado (CMU)*; Abhinav Gupta (CMU/FAIR),,,Oral,http://arxiv.org/abs/2203.12710,,,, Deep Radial Embedding for Visual Sequence Learning,"Yuecong Min (Institute of Computing Technology, Chinese Academy of Sciences); Peiqi Jiao (Institute of Computing Technology, Chinese Academy of Sciences); Yanan Li (Xiaomi); Wang Xiaotao (XIaomi); LEI LEI (Xiaomi); Xiujuan Chai (Agricultural Information Institute, Chinese); Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)*",,,Oral,,,,, Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons,Oren Katzir (Tel Aviv University)*; Dani Lischinski (The Hebrew University of Jerusalem); Danny Cohen-Or (Tel Aviv University),,,Oral,,,,, -3D Object Detection with a Self-supervised Lidar Scene Flow Backbone,Emeç Erçelik (Technical University of Munich)*; Ekim Yurtsever (The Ohio State University); Mingyu Liu (TUM); Zhijie Yang (Technical University of Munich); Hanzhen Zhang (TUM); Pınar Topçam (Technical University of Munich ); Maximilian Listl (Technical University of Munich); Yılmaz Kaan Kaan Çaylı (Technical University of Munich); Alois C. Knoll (Robotics and Embedded Systems),,,Oral,http://arxiv.org/abs/2205.00705,https://github.com/emecercelik/ssl-3d-detection.git,,, +3D Object Detection with a Self-supervised Lidar Scene Flow Backbone,Emeç Erçelik (Technical University of Munich)*; Ekim Yurtsever (The Ohio State University); Mingyu Liu (TUM); Zhijie Yang (Technical University of Munich); Hanzhen Zhang (TUM); Pınar Topçam (Technical University of Munich ); Maximilian Listl (Technical University of Munich); Yılmaz Kaan Kaan Çaylı (Technical University of Munich); Alois C. Knoll (Robotics and Embedded Systems),,,Oral,http://arxiv.org/abs/2205.00705,https://github.com/emecercelik/ssl-3d-detection.git,,, FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-world Point Clouds,lihe Ding (Beijing Institute of Technology)*; Shaocong Dong (Beijing Institute of Technology); Tingfa Xu (Beijing Institute of Technology); xinli Xu (Beijing Institute of Technology); Jie Wang (Beijing Institute of Technology); Jianan Li (Beijing Institute of Technology),,,Oral,,,,, Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting,Yangzheng Wu (Queen's University)*; Mohsen Zand (Queen's University); Ali Etemad (Queen's University); Michael Alan Greenspan (Queen's University),,,Oral,,,,, Flow graph to Video Grounding for Weakly-supervised Multi-Step Localization,NIKITA DVORNIK (Samsung)*; Isma Hadji (Samsung AI Center - Toronto); Hai X Pham (Samsung AI Center); Dhaivat Bhatt (Samsung); Brais Martinez (Samsung AI Center); Afsaneh Fazly (SAIC Toronto); Allan D Jepson (Samsung Toronto AIC),,,Oral,,,,, @@ -155,7 +154,7 @@ Unsupervised Pose-aware Part Decomposition for Man-made Articulated Objects,Yuki Cartoon Explanations of Image Classifiers,"Stefan Kolek (LMU)*; Duc Anh Nguyen (LMU Munich); Ron Levie (Technion); Joan Bruna (Courant Institute of Mathematical Sciences, NYU, USA); Gitta Kutyniok (Ludwig Maximilian University of Munich)",,,Oral,http://arxiv.org/abs/2110.03485,,,, RRSR:Reciprocal Reference-based Image Super-Resolution with Progressive Feature Alignment and Selection,"Lin Zhang (CASIA); Xin Li (Baidu); Dongliang He (Baidu)*; Fu Li (Baidu); Yili Wang (Tsinghua University); Zhaoxiang Zhang (Chinese Academy of Sciences, China)",,,Oral,,,,, Gaussian Activated Neural Radiance Fields for High Fidelity Reconstruction & Pose Estimation,Shin-Fang Chng (The University of Adelaide)*; Sameera Ramasinghe (University of Adelaide); Jamie Sherrah (AIML); Simon Lucey (University of Adelaide),,,Oral,,,,, -Unbiased Gradient Estimation for Differentiable Surface Splatting via Poisson Sampling,Jan U. Müller (University of Bonn)*; Michael Weinmann (TU Delft); Reinhard Klein (University of Bonn),,,Oral,,,,, +Unbiased Gradient Estimation for Differentiable Surface Splatting via Poisson Sampling,Jan U. Müller (University of Bonn)*; Michael Weinmann (TU Delft); Reinhard Klein (University of Bonn),,,Oral,,,,, """This is my unicorn, Fluffy"": Personalizing frozen vision-language representations",Niv Cohen (The Hebrew University of Jerusalem)*; Rinon Gal (Tel Aviv University); Eli Meirom (NVIDIA Research); Gal Chechik (NVIDIA); Yuval Atzmon (NVIDIA Research),,,Oral,http://arxiv.org/abs/2204.01694,,,, Learning Uncoupled-Modulation CVAE for 3D Action-Conditioned Human Motion Synthesis,"Chongyang Zhong (Institute of Computing Technology, Chinese Academy of Sciences)*; Lei Hu (Institute of Computing Technology, Chinese Academy of Sciences ); Zihao Zhang (Institute of Computing Technology, Chinese Academy of Sciences); Shihong Xia (institute of computing technology of the Chinese academy of sciences)",,,Poster,,,,, Generative Domain Adaptation for Face Anti-Spoofing,"Qianyu Zhou (Shanghai Jiao Tong University)*; Ke-Yue Zhang (YouTu Lab, Tencent); Taiping Yao (Tencent YouTu); Ran Yi (Shanghai Jiao Tong University); Kekai Sheng (Youtu Lab, Tencent Inc.); Shouhong Ding (Tencent); Lizhuang Ma (Shanghai Jiao Tong University)",,,Poster,http://arxiv.org/abs/2207.10015,,,, @@ -165,7 +164,7 @@ PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estim Understanding the Dynamics of DNNs Using Graph Modularity,Yao Lu (Zhejiang University of Technology)*; Wen Yang (Zhejiang University of Technology); Yunzhe Zhang (Zhejiang University of Technology); Zuohui Chen (Zhejiang University of Technology); Jinyin Chen (Zhejiang University of Technology); Qi Xuan (Zhejiang University of Technology); Zhen Wang (Northwestern Polytechnical University); Xiaoniu Yang (Zhejiang University of Technology; Science and Technology on Communication Information Security Control Laboratory),,,Poster,http://arxiv.org/abs/2111.12485,https://github.com/yaolu-zjut/Dynamic-Graphs-Construction,,, Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective,Quan Cui (Waseda University)*; Bingchen Zhao (University of Edinburgh); Zhao-Min Chen (NanJing University); Borui Zhao (Megvii Technology); Renjie Song (Megvii Inc.); Boyan Zhou (ByteDance); Jiajun Liang (Megvii); Osamu Yoshie (Waseda University),,,Poster,,,,, Learning-based Point Cloud Registration for 6D Object Pose Estimation in the Real World,"Zheng Dang (EPFL)*; Lizhou Wang (Xi'an Jiaotong University); Yu Guo (School of Software Engineering, Xi'an Jiaotong University); Mathieu Salzmann (EPFL)",,,Poster,,,,, -AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing,Jiaxi Jiang (ETH Zurich)*; Paul Streli (ETH Zurich); Huajian Qiu (EPFL); Andreas R Fender (ETH Zurich); Larissa Laich (Facebook Reality Labs); Patrick Snape (Meta); Christian Holz (ETH Zürich),,,Poster,http://arxiv.org/abs/2207.13784,,,, +AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing,Jiaxi Jiang (ETH Zurich)*; Paul Streli (ETH Zurich); Huajian Qiu (EPFL); Andreas R Fender (ETH Zurich); Larissa Laich (Facebook Reality Labs); Patrick Snape (Meta); Christian Holz (ETH Zürich),,,Poster,http://arxiv.org/abs/2207.13784,,,, Knowledge Condensation Distillation,"chenxin li (Xiamen University)*; Mingbao Lin (Xiamen University, China); Zhiyuan Ding (Xiamen University); Nie Lin (Hunan University); Yihong Zhuang (Xiamen University); Yue Huang (Xiamen University); Xinghao Ding (Xiamen University); Liujuan Cao (Xiamen University)",,,Poster,http://arxiv.org/abs/2207.05409,https://github.com/dzy3/KCD,,, CAR: Class-aware Regularizations for Semantic Segmentation,Ye Huang (University of Technology Sydney)*; Di Kang (Tencent); Liang Chen (Fujian Normal University); Xuefei Zhe (Tencent AI lab); Wenjing Jia (University of Technology Sydney); Linchao Bao (Tencent AI Lab); Xiangjian He (University of Nottingham Ningbo China),,,Poster,http://arxiv.org/abs/2203.07160,https://github.com/edwardyehuang/CAR,,, Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation,Yuyang Zhao (National University of Singapore)*; Zhun Zhong (University of Trento); Na Zhao (NUS); Nicu Sebe (University of Trento); Gim Hee Lee (National University of Singapore),,,Poster,http://arxiv.org/abs/2204.02548,,,, @@ -178,10 +177,10 @@ Contrastive Prototypical Network with Wasserstein Confidence Penalty,Haoqing Wan Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain,"Jiazhen Ji (Tencent)*; Huan Wang (Xiamen University); Yuge Huang (Tencent YouTu); Jiaxiang Wu (Tencent); Xingkun Xu (Tencent); Shouhong Ding (Tencent); ShengChuan Zhang (Xiamen University); Liujuan Cao (Xiamen University); Rongrong Ji (Xiamen University, China)",,,Poster,http://arxiv.org/abs/2207.07316,,,, An End-to-End Transformer Model for Crowd Localization,Dingkang Liang (Huazhong University of Science and Technology)*; Wei Xu (Beijing University of Posts and Telecommunications); Xiang Bai (Huazhong University of Science and Technology),,,Poster,http://arxiv.org/abs/2202.13065,,,, Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection,Zehui Chen (University of Science and Technology of China); Zhenyu Li (Harbin Institute of Technology); Shiquan Zhang (SenseTime Research); Liangji Fang (Sensetime Research); Qinhong Jiang (SenseTime Research; Shanghai AI Laboratory); Feng Zhao (University of Science and Technology of China)*,,,Poster,,https://github.com/zehuichen123/AutoAlignV2,,, -Masked Generative Distillation,"Zhendong Yang (Graduate school at ShenZhen，Tsinghua university)*; Zhe Li (Bytedance Inc.); Shao Mingqi (Graduate school at ShenZhen, Tsinghua university); Dachuan Shi (Graduate school at ShenZhen, Tsinghua University); Zehuan Yuan (Bytedance.Inc); Chun Yuan (Graduate school at ShenZhen，Tsinghua university)",,,Poster,http://arxiv.org/abs/2205.01529,https://github.com/yzd-v/MGD,,, +Masked Generative Distillation,"Zhendong Yang (Graduate school at ShenZhen，Tsinghua university)*; Zhe Li (Bytedance Inc.); Shao Mingqi (Graduate school at ShenZhen, Tsinghua university); Dachuan Shi (Graduate school at ShenZhen, Tsinghua University); Zehuan Yuan (Bytedance.Inc); Chun Yuan (Graduate school at ShenZhen，Tsinghua university)",,,Poster,http://arxiv.org/abs/2205.01529,https://github.com/yzd-v/MGD,,, Saliency Hierarchy Modeling via Generative Kernels for Salient Object Detection,Wenhu Zhang (Zhejiang University)*; Liangli Zheng (Zhejiang University); Huanyu Wang (Zhejiang University); Xintian Wu (Zhejiang University); Xi Li (Zhejiang University),,,Poster,,,,, Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification,"Renrui Zhang (Shanghai AI Lab)*; Zhang Wei (Shanghai AI-Lab); Rongyao Fang (Chinese University of Hong Kong); Peng Gao (Chinese university of hong kong); Kunchang Li (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences); Jifeng Dai (SenseTime); Yu Qiao (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences); Hongsheng Li (The Chinese University of Hong Kong)",,,Poster,,,,, -Temporal Lift Pooling for Continuous Sign Language Recognition,"Lianyu Hu (Tianjin University)*; Liqing Gao (College of Intelligence and Computing，Tianjin University); Zekang Liu (College of Intelligence and Computing, Tianjin University); Wei Feng (College of Intelligence and Computing, Tianjin University, China)",,,Poster,http://arxiv.org/abs/2207.08734,,,, +Temporal Lift Pooling for Continuous Sign Language Recognition,"Lianyu Hu (Tianjin University)*; Liqing Gao (College of Intelligence and Computing，Tianjin University); Zekang Liu (College of Intelligence and Computing, Tianjin University); Wei Feng (College of Intelligence and Computing, Tianjin University, China)",,,Poster,http://arxiv.org/abs/2207.08734,,,, MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes,Yang Jiao (Fudan University)*; Shaoxiang Chen (Fudan University); Zequn Jie (Meituan inc.); Jingjing Chen (Fudan University); Lin Ma (Meituan); Yu-Gang Jiang (Fudan University),,,Poster,http://arxiv.org/abs/2203.05203,https://github.com/SxJyJay/MORE,,, JPEG Artifacts Removal via Contrastive Representation Learning,Xi Wang (University of Science and Technology of China); Xueyang Fu (University of Science and Technology of China)*; Yurui Zhu (University of Science and Technology of China); Zheng-Jun Zha (University of Science and Technology of China),,,Poster,,,,, Tackling Long-Tailed Category Distribution Under Domain Shifts,"Xiao Gu (Imperial College London)*; Yao Guo (Shanghai Jiao Tong Univerisity); Zeju Li (Imperial College London); Jianing Qiu (Imperial College London); DOU QI (The Chinese University of Hong Kong); Yuxuan Liu (Institude of Medical Robotics, Shanghai Jiao Tong University); Benny P L Lo (Imperial College London); Guang-Zhong Yang (SJTU)",,,Poster,http://arxiv.org/abs/2207.10150,,,, @@ -191,7 +190,7 @@ Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network,Zhe ExtrudeNet: Unsupervised Inverse Sketch-and-Extrude for Shape Parsing,Daxuan Ren (Nanyang Technological University)*; Jianmin Zheng (Nanyang Technological University); Jianfei Cai (Monash University); jiatong j li (Sensetime); Junzhe Zhang (Nanyang Technological University),,,Poster,,,,, P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation,"Wenkang Shan (Peking University)*; Zhenhua Liu (Peking University); xinfeng zhang (University of Chinese Academy of Sciences); Shanshe Wang (Peking University); Siwei Ma (Peking University, China); Wen Gao (PKU)",,,Poster,,,,, Contrast-Phys: Unsupervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast,Zhaodong Sun (University of Oulu)*; Xiaobai Li (University of Oulu),,,Poster,,,,, -Panoptic Scene Graph Generation,Jingkang Yang (Nanyang Technological University)*; Yi Zhe Ang (Nanyang Technological University); Zujin GUO (Nanyang Technological University); Kaiyang Zhou (Nanyang Technological University); Wayne Zhang (SenseTime Research); Ziwei Liu (Nanyang Technological University),,,Poster,http://arxiv.org/abs/2207.11247,,,, +Panoptic Scene Graph Generation,Jingkang Yang (Nanyang Technological University)*; Yi Zhe Ang (Nanyang Technological University); Zujin GUO (Nanyang Technological University); Kaiyang Zhou (Nanyang Technological University); Wayne Zhang (SenseTime Research); Ziwei Liu (Nanyang Technological University),,,Poster,http://arxiv.org/abs/2207.11247,https://github.com/Jingkang50/OpenPSG,https://huggingface.co/spaces/ECCV2022/PSG,, StyleSwap: Style-Based Generator Empowers Robust Face Swapping,"Zhiliang Xu (Baidu Inc.); Hang Zhou (The Chinese University of Hong Kong)*; Zhibin Hong (Baidu Inc.); Ziwei Liu (Nanyang Technological University); Jiaming Liu (Baidu Inc.); zhizhi guo (Department of Computer Vision Technology (VIS), Baidu Inc); Junyu Han (Baidu Inc.); jingtuo liu (baidu); Errui Ding (Baidu Inc.); Jingdong Wang (Baidu)",,,Poster,,,,, Boosting Event Stream Super-Resolution with A Recurrent Neural Network,Wenming Weng (University of Science and Technology of China)*; Yueyi Zhang (University of Science and Technology of China); Zhiwei Xiong (University of Science and Technology of China),,,Poster,,,,, Unknown-Oriented Learning for Open Set Domain Adaptation,jie liu (City University of Hong Kong)*; Xiaoqing Guo (City University of Hong Kong); Yixuan YUAN (City University of Hong Kong),,,Poster,,,,, @@ -221,29 +220,29 @@ Source-Free Domain Adaptation with Contrastive Domain Alignment and Self-supervi MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection,Xuesong Chen (The Chinese University of Hong Kong)*; Shaoshuai Shi (MPI Informatics); Benjin Zhu (MEGVII); Ka Chun Cheung (Nvidia); Hang Xu (Huawei Noah's Ark Lab); Hongsheng Li (The Chinese University of Hong Kong),,,Poster,http://arxiv.org/abs/2205.05979,,,, SdAE: Self-distillated Masked Autoencoder,Yabo Chen (Shanghai Jiao Tong University ); Yuchen Liu (Shanghai Jiao Tong university); Dongsheng Jiang (Huawei Cloud & AI); xiaopeng zhang (Huawei Cloud EI )*; Wenrui Dai (Shanghai Jiao Tong University); Hongkai Xiong (Shanghai Jiao Tong University); Qi Tian (Huawei Cloud & AI),,,Poster,http://arxiv.org/abs/2208.00449,https://github.com/AbrahamYabo/SdAE,,, A Transformer-based Decoder for Semantic Segmentation with Multi-level Context Mining,Bowen Shi (Shanghai Jiao Tong University)*; Dongsheng Jiang (Huawei Cloud & AI); xiaopeng zhang (Huawei Cloud EI ); Han Li (Shanghai Jiao Tong University); Wenrui Dai (Shanghai Jiao Tong University); Junni Zou (Shanghai Jiao Tong University); Hongkai Xiong (Shanghai Jiao Tong University); Qi Tian (Huawei Cloud & AI),,,Poster,,,,, -Graph-constrained Contrastive Regularization for Semi-weakly Volumetric Segmentation,"Simon Reiß (Karlsruhe Institute of Technology)*; Constantin Marc Seibold (Karlsruhe Institute of Technology); Alexander Freytag (Carl Zeiss AG, Jena, Germany); Rodner Erik (University of Applied Sciences Berlin); Rainer Stiefelhagen (Karlsruhe Institute of Technology)",,,Poster,,,,, +Graph-constrained Contrastive Regularization for Semi-weakly Volumetric Segmentation,"Simon Reiß (Karlsruhe Institute of Technology)*; Constantin Marc Seibold (Karlsruhe Institute of Technology); Alexander Freytag (Carl Zeiss AG, Jena, Germany); Rodner Erik (University of Applied Sciences Berlin); Rainer Stiefelhagen (Karlsruhe Institute of Technology)",,,Poster,,,,, Improving Vision Transformers by Revisiting High-frequency Components,Jiawang Bai (Tsinghua University)*; Li Yuan (Peking University); Shu-Tao Xia (Tsinghua University); Shuicheng Yan (Sea AI Labs); Zhifeng Li (Tencent AI Lab); Wei Liu (Tencent),,,Poster,http://arxiv.org/abs/2204.00993,https://github.com/jiawangbai/HAT,,, Adaptive Co-Teaching for Unsupervised Monocular Depth Estimation,Weisong Ren (Dalian University of Technology); Lijun Wang (Dalian University of Technology)*; Yongri Piao (Dalian University of Technology); Miao Zhang (Dalian University of Technology); Huchuan Lu (Dalian University of Technology); Ting Liu (Alibaba),,,Poster,,,,, FurryGAN: High quality foreground-aware image synthesis,Jeongmin Bae (Yonsei University); Mingi Kwon (Yonsei University); Youngjung Uh (Yonsei University)*,,,Poster,http://arxiv.org/abs/2208.10422,,,, An Efficient Spatio-Temporal Pyramid Transformer for Action Detection,"Yuetian Weng (Monash University); Zizheng Pan (Monash University); Mingfei Han (Monash University; DATA61, CSIRO); Xiaojun Chang (University of Technology Sydney); Bohan Zhuang (Monash University)*",,,Poster,http://arxiv.org/abs/2207.10448,,,, LocVTP: Video-Text Pre-training for Temporal Localization,Meng Cao (Peking University); Tianyu Yang (Tencent AI Lab); Junwu Weng (Tencent AI Lab); Can Zhang (Peking University); Jue Wang (Tencent AI Lab); Yuexian Zou (Peking University)*,,,Poster,http://arxiv.org/abs/2207.10362,,,, Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects,Chen Zhao (EPFL)*; Yinlin Hu (EPFL); Mathieu Salzmann (EPFL),,,Poster,http://arxiv.org/abs/2203.08472,,,, -Online Segmentation of LiDAR Sequences: Dataset and Algorithm,Romain Loiseau (École des ponts ParisTech)*; Mathieu Aubry (École des ponts ParisTech); loic landrieu (IGN),,,Poster,http://arxiv.org/abs/2206.08194,,,, +Online Segmentation of LiDAR Sequences: Dataset and Algorithm,Romain Loiseau (École des ponts ParisTech)*; Mathieu Aubry (École des ponts ParisTech); loic landrieu (IGN),,,Poster,http://arxiv.org/abs/2206.08194,,,, MVSTER: Epipolar Transformer for Efficient Multi-View Stereo,"Xiaofeng Wang (Institute of Automation, Chinese Academy of Sciences; School of Artificial Intelligence, University of Chinese Academy of Sciences)*; Zheng Zhu (Tsinghua University); Guan Huang (Institute of Automation, Chinese Academy of Sciences); Fangbo Qin (Institute of Automation, Chinese Academy of Sciences); Yun Ye (XForwardAI Technology Co., Ltd, Beijing, China); Yijia He (Beijing Kuaishou Technology Co., Ltd); Xu Chi (Phigent Robotics); Xingang Wang (Institute of Automation, CAS)",,,Poster,http://arxiv.org/abs/2204.07346,,,, Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction,Haocheng Yuan (Northwestern Polytechnical University); Chen Zhao (EPFL); Shichao Fan (Northwestern Polytechnical University); Jiaxi Jiang (Northwestern Polytechnical University); Jiaqi Yang (Northwestern Polytechnical University)*,,,Poster,http://arxiv.org/abs/2203.10212,,,, Generalizable Medical Image Segmentation via Random Amplitude Mixup and Domain-Specific Image Restoration,Ziqi Zhou (Nanjing University)*; Lei Qi (Southeast University); Yinghuan Shi (Nanjing University),,,Poster,http://arxiv.org/abs/2208.03901,,,, -Demystifying Unsupervised Semantic Correspondence Estimation,Mehmet Aygün (The University of Edinburgh)*; Oisin Mac Aodha (University of Edinburgh),,,Poster,http://arxiv.org/abs/2207.05054,,,, +Demystifying Unsupervised Semantic Correspondence Estimation,Mehmet Aygün (The University of Edinburgh)*; Oisin Mac Aodha (University of Edinburgh),,,Poster,http://arxiv.org/abs/2207.05054,,,, Learning Shadow Correspondence for Video Shadow Detection,Xinpeng Ding (The Hong Kong University of Science and Technology); Jingwen Yang (The Hong Kong University of Science and Technology); Xiaowei Hu (Shanghai AI Laboratory); Xiaomeng Li (The Hong Kong University of Science and Technology)*,,,Poster,http://arxiv.org/abs/2208.00150,,,, -PolarMOT: How far can geometric relations take us in 3D multi-object tracking?,Aleksandr Kim (Technical University of Munich); Guillem Brasó (TUM); Aljosa Osep (TUM Munich)*; Laura Leal-Taixé (TUM),,,Poster,http://arxiv.org/abs/2208.01957,,,, +PolarMOT: How far can geometric relations take us in 3D multi-object tracking?,Aleksandr Kim (Technical University of Munich); Guillem Brasó (TUM); Aljosa Osep (TUM Munich)*; Laura Leal-Taixé (TUM),,,Poster,http://arxiv.org/abs/2208.01957,,,, Few-Shot End-to-End Object Detection via Constantly Concentrated Encoding across Heads,Jiawei Ma (Columbia University)*; Guangxing Han (Columbia University); Shiyuan Huang (Columbia University); Yuncong Yang (Columbia University); Shih-Fu Chang (Columbia University),,,Poster,,,,, MVDECOR: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation,"Gopal Sharma (University of Massachusetts Amherst)*; Kangxue Yin (NVIDIA); Subhransu Maji (University of Massachusetts, Amherst); Evangelos Kalogerakis (UMass Amherst); Or Litany (NVIDIA); Sanja Fidler (University of Toronto, NVIDIA)",,,Poster,http://arxiv.org/abs/2208.08580,,,, -Implicit Neural Representations for Image Compression,"Yannick Strümpler (ETH Zürich)*; Janis Postels (ETH Zurich); Ren Yang (ETH Zurich); Luc Van Gool (ETH Zurich); Federico Tombari (Google, TU Munich)",,,Poster,http://arxiv.org/abs/2112.04267,,,, +Implicit Neural Representations for Image Compression,"Yannick Strümpler (ETH Zürich)*; Janis Postels (ETH Zurich); Ren Yang (ETH Zurich); Luc Van Gool (ETH Zurich); Federico Tombari (Google, TU Munich)",,,Poster,http://arxiv.org/abs/2112.04267,,,, Cross-modal Prototype Driven Network for Radiology Report Generation,Jun Wang (University of Warwick)*; Abhir Bhalerao (University of Warwick); Yulan He (University of Warwick),,,Poster,http://arxiv.org/abs/2207.04818,,,, -Scene Text Recognition with Permuted Autoregressive Sequence Models,Darwin Bautista (University of the Philippines)*; Rowel Atienza (University of the Philippines),,,Poster,http://arxiv.org/abs/2207.06966,https://github.com/baudm/parseq,,, +Scene Text Recognition with Permuted Autoregressive Sequence Models,Darwin Bautista (University of the Philippines)*; Rowel Atienza (University of the Philippines),,,Poster,http://arxiv.org/abs/2207.06966,https://github.com/baudm/parseq,https://huggingface.co/spaces/ECCV2022/PARSeq-OCR,, XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model,Ho Kei Cheng (University of Illinois Urbana-Champaign)*; Alexander Schwing (UIUC),,,Poster,http://arxiv.org/abs/2207.07115,,,, SUPR: A Sparse Unified Part-Based Human Body Model,Ahmed A A Osman (Max Planck Institute for Intelligent Systems)*; Michael J. Black (Max Planck Institute for Intelligent Systems); Timo Bolkart (Max Planck Institute for Intelligent Systems); Dimitrios Tzionas (University of Amsterdam),,,Poster,,,,, SCAM! Transferring humans between images with Semantic Cross Attention Modulation,Nicolas Dufour (ENPC)*; David Picard (ENPC); Vicky Kalogeiton (Ecole Polytechnique),,,Poster,,,,, -Q-FW: A Hybrid Classical-Quantum Frank-Wolfe for Quadratic Binary Optimization,Alp Yurtsever (Umeå University); Tolga Birdal (TU Munich)*; Vladislav Golyanik (MPI for Informatics),,,Poster,,,,, +Q-FW: A Hybrid Classical-Quantum Frank-Wolfe for Quadratic Binary Optimization,Alp Yurtsever (UmeÃ¥ University); Tolga Birdal (TU Munich)*; Vladislav Golyanik (MPI for Informatics),,,Poster,,,,, Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach,Rolandos Alexandros Potamias (Imperial College London)*; Giorgos Bouritsas (Imperial College London); Stefanos Zafeiriou (Imperial College London),,,Poster,http://arxiv.org/abs/2109.14982,,,, Neural Architecture Search for Spiking Neural Networks,Youngeun Kim (Yale University)*; Yuhang Li (Yale University); Hyoungseob Park (Yale University); Yeshwanth Venkatesha (Yale university); Priyadarshini Panda (Yale University),,,Poster,http://arxiv.org/abs/2201.10355,,,, Neuromorphic Data Augmentation for Training Spiking Neural Networks,Yuhang Li (Yale University)*; Youngeun Kim (Yale University); Hyoungseob Park (Yale University); Tamar Geller (Yale University); Priyadarshini Panda (Yale University),,,Poster,http://arxiv.org/abs/2203.06145,https://github.com/Intelligent-Computing-Lab-Yale/NDA_SNN,,, @@ -260,7 +259,7 @@ TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Huma Self-Distillation for Robust LiDAR Semantic Segmentation in Autonomous Driving,Jiale Li (Zhejiang University); Hang Dai (Mohamed bin Zayed University of Artificial Intelligence)*; Yong Ding (Zhejiang University),,,Poster,,,,, Semi-Supervised Monocular 3D Object Detection by Multi-View Consistency,"Qing Lian (Hong Kong University of Science and Technology )*; Yanbo XU (The Hong Kong University of Science and Technology); Weilong Yao (Shanghai Xiantu Intelligent Technology Co., Ltd.); Yingcong Chen (Hong Kong University of Science and Technology); Tong Zhang (Hong Kong University of Science and Technology)",,,Poster,,,,, Lidar Point Cloud Guided Monocular 3D Object Detection,Liang Peng (ZJU)*; Fei Liu (Zhejiang University); Zhengxu Yu (Zhejiang University); Senbo Yan (Zhejiang University); Dan Deng (FABU); Zheng Yang (FABU); Haifeng Liu (ZJU); Deng Cai (ZJU),,,Poster,http://arxiv.org/abs/2104.09035,https://github.com/SPengLiang/LPCG,,, -Structural Causal 3D Reconstruction,"Weiyang Liu (University of Cambridge)*; Zhen Liu (Mila, University of Montreal); Liam Paull (Université de Montréal); Adrian Weller (University of Cambridge); Bernhard Schölkopf (MPI for Intelligent Systems, Tübingen)",,,Poster,http://arxiv.org/abs/2207.10156,,,, +Structural Causal 3D Reconstruction,"Weiyang Liu (University of Cambridge)*; Zhen Liu (Mila, University of Montreal); Liam Paull (Université de Montréal); Adrian Weller (University of Cambridge); Bernhard Schölkopf (MPI for Intelligent Systems, Tübingen)",,,Poster,http://arxiv.org/abs/2207.10156,,,, KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo,Yikang Ding (Tsinghua University)*; Qingtian Zhu (Peking University); Xiangyue Liu (Beihang University); Wentao Yuan (Peking Universtiy); Haotian Zhang (Megvii); Chi Zhang (Megvii Inc.),,,Poster,,,,, When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition,Bohan Li (Huazhong University of Science and Technology)*; Ye Yuan (Tomorrow Advancing Life); Dingkang Liang (Huazhong University of Science and Technology); Xiao Liu (Tencent); zhilong ji (Tomorrow Advancing Life); Jinfeng Bai (TAL); Wenyu Liu (Huazhong University of Science and Technology); Xiang Bai (Huazhong University of Science and Technology),,,Poster,http://arxiv.org/abs/2207.11463,https://github.com/LBH1024/CAN,,, Shape Matters: Deformable Patch Attack,Zhaoyu Chen (Fudan University); Bo Li (Nanjing University)*; Shuang Wu (Tencent); Jianghe Xu (Tencent Youtu Lab); Shouhong Ding (Tencent); Wenqiang Zhang (Fudan University),,,Poster,,,,, @@ -275,25 +274,25 @@ CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS,Zix RigNet: Repetitive Image Guided Network for Depth Completion,Zhiqiang Yan (Nanjing University of Science and Tenchnology)*; Kun Wang (Nanjing University of Science and Technology); Xiang Li (Nanjing University of Science and Technology); Zhenyu Zhang (Tencent); Jun Li (Nanjing University of Science and Technology); Jian Yang (Nanjing University of Science and Technology),,,Poster,http://arxiv.org/abs/2107.13802,,,, Streamable Neural Fields,Junwoo Cho (Sungkyunkwan University)*; Seungtae Nam (Sungkyunkwan University); Daniel Rho (Sungkyunkwan University); Jong Hwan Ko (Sungkyunkwan University); Eunbyung Park (Sungkyunkwan University),,,Poster,http://arxiv.org/abs/2207.09663,,,, 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds,"Xu Yan (The Chinese University of Hong Kong, Shenzhen); Jiantao Gao (Shanghai University); Chaoda Zheng (The Chinese University of Hong Kong, Shen Zhen); chao zheng (Tencent); Ruimao Zhang (The Chinese University of Hong Kong, Shenzhen); Shuguang Cui (The Chinese University of Hong Kong, Shenzhen ); Zhen Li (The Chinese University of Hong Kong, Shenzhen)*",,,Poster,http://arxiv.org/abs/2207.04397,,,, -Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification,"Yang Liu (Beihang University); Lei Zhou (Beihang University)*; Pengcheng Zhang (Beihang University); Xiao Bai (Beihang University); Lin Gu (RIKEN，AIP / The University of Tokyo); Xiaohan Yu (Griffith University); Jun Zhou (Griffith University); Hancock Edwin (""University of York, UK"")",,,Poster,,,,, +Where to Focus: Investigating Hierarchical Attention Relationship for Fine-Grained Visual Classification,"Yang Liu (Beihang University); Lei Zhou (Beihang University)*; Pengcheng Zhang (Beihang University); Xiao Bai (Beihang University); Lin Gu (RIKEN，AIP / The University of Tokyo); Xiaohan Yu (Griffith University); Jun Zhou (Griffith University); Hancock Edwin (""University of York, UK"")",,,Poster,,,,, Mind the Gap in Distilling StyleGANs,Guodong Xu (The Chinese University of Hong Kong)*; Yuenan HOU (Shanghai AI Lab); Ziwei Liu (Nanyang Technological University); Chen Change Loy (Nanyang Technological University),,,Poster,http://arxiv.org/abs/2208.08840,,,, -End-to-End Active Speaker Detection,Juan C Leon (KAUST)*; Moritz Cordes (Leuphana University of Lüneburg); Chen Zhao (KAUST); Bernard Ghanem (KAUST),,,Poster,http://arxiv.org/abs/2203.14250,https://github.com/fuankarion/end-to-end-asd,,, +End-to-End Active Speaker Detection,Juan C Leon (KAUST)*; Moritz Cordes (Leuphana University of Lüneburg); Chen Zhao (KAUST); Bernard Ghanem (KAUST),,,Poster,http://arxiv.org/abs/2203.14250,https://github.com/fuankarion/end-to-end-asd,,, Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing,Haoyue Cheng (Nanjing University); Zhaoyang Liu (SenseTime Research); Hang Zhou (The Chinese University of Hong Kong); Chen Qian (SenseTime); Wayne Wu (SenseTime Research); Limin Wang (Nanjing University)*,,,Poster,http://arxiv.org/abs/2204.11573,https://github.com/MCG-NJU/JoMoLD,,, Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition,Xinyi Zou (Xiamen University); Yan Yan (Xiamen University)*; Jing-Hao Xue (University College London); Si Chen (Xiamen University of Technology); Hanzi Wang (Xiamen University),,,Poster,,,,, Learning with Recoverable Forgetting,Jingwen Ye (National University of Singapore)*; Fu Yifang (National University of Singapore); Jie Song (Zhejiang University); Xingyi Yang (National University of Singapore); Songhua Liu (National University of Singapore); Xin Jin (University of Science and Technology of China); Mingli Song (Zhejiang University); Xinchao Wang (National University of Singapore),,,Poster,http://arxiv.org/abs/2207.08224,,,, Masked Autoencoders for Point Cloud Self-supervised Learning,"Yatian Pang (National University of Singapore); Wenxiao Wang (State Key Lab of CAD&CG, Zhejiang University); Francis EH Tay (National University of Singapore); Wei Liu (Tencent); Yonghong Tian (Peking University); Li Yuan (Peking University)*",,,Poster,http://arxiv.org/abs/2203.06604,,,, RamGAN: Region Attentive Morphing GAN for Region-Level Makeup Transfer,Jianfeng Xiang (ShenZhen University)*; Junliang Chen (Shenzhen University); Wenshuang Liu (Shenzhen University); Xianxu Hou (Shenzhen University); Linlin Shen (Shenzhen University),,,Poster,,,,, -Efficient One Pass Self-distillation with Zipf's Label Smoothing,Jiajun Liang (Megvii)*; Linze Li (MEGVII Technology); Zhaodong Bing (Megvii Technology); Borui Zhao (Megvii Technology); Yao Tang (Peking University); Bo Lin (MEGVII Technology); Haoqiang Fan (Megvii Inc（face++）),,,Poster,http://arxiv.org/abs/2207.12980,https://github.com/megvii-research/zipfls,,, +Efficient One Pass Self-distillation with Zipf's Label Smoothing,Jiajun Liang (Megvii)*; Linze Li (MEGVII Technology); Zhaodong Bing (Megvii Technology); Borui Zhao (Megvii Technology); Yao Tang (Peking University); Bo Lin (MEGVII Technology); Haoqiang Fan (Megvii Inc（face++）),,,Poster,http://arxiv.org/abs/2207.12980,https://github.com/megvii-research/zipfls,,, DaViT: Dual Attention Vision Transformers,Mingyu Ding (The University of Hong Kong)*; Bin Xiao (Microsoft); Noel C Codella (Microsoft); Ping Luo (The University of Hong Kong); Jingdong Wang (Baidu); Lu Yuan (Microsoft),,,Poster,http://arxiv.org/abs/2204.03645,https://github.com/dingmyu/davit,,, OneFace: One Threshold for All,Jiaheng Liu (Beihang University); zhipeng yu (University of Chinese Academy of Sciences); Haoyu Qin (SenseTime); Yichao Wu (Sensetime Group Limited); Ding Liang (Sensetime Group Limited); Gangming Zhao (The University of Hong Kong); Ke Xu (Beihang University)*,,,Poster,,,,, -Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization,Yunpeng Bai (Tsinghua University )*; Chao Dong (SIAT); Zenghao Chai (Tsinghua University); Andong Wang (Tsinghua University); Zhengzhuo Xu (Tsinghua University); Chun Yuan (Graduate school at ShenZhen，Tsinghua university),,,Poster,http://arxiv.org/abs/2112.01335,,,, +Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization,Yunpeng Bai (Tsinghua University )*; Chao Dong (SIAT); Zenghao Chai (Tsinghua University); Andong Wang (Tsinghua University); Zhengzhuo Xu (Tsinghua University); Chun Yuan (Graduate school at ShenZhen，Tsinghua university),,,Poster,http://arxiv.org/abs/2112.01335,,,, Vibration-based Uncertainty Estimation for Learning from Limited Supervision,Hengtong Hu (Hefei University of Technology)*; Lingxi Xie (Huawei Inc.); Xinyue Huo (University of Science and Technology of China); Richang Hong (HeFei University of Technology); Qi Tian (Huawei Cloud & AI),,,Poster,,,,, SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognition,Victor A Escorcia (Samsung AI Center)*; Ricardo Guerrero (Samsung AI Center Cambridge); Xiatian Zhu (Samsung AI Centre); Brais Martinez (Samsung AI Center),,,Poster,http://arxiv.org/abs/2204.04796,,,, FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling,Hao Lu (Huazhong University of Science and Technology); Wenze Liu (Huazhong university of science and technology); Hongtao Fu (Huazhong university of Science and Technology); Zhiguo Cao (Huazhong Univ. of Sci.&Tech.)*,,,Poster,http://arxiv.org/abs/2207.10392,,,, VTC: Improving Video-Text Retrieval with User Comments,Laura Hanu (Unitary)*; James Thewlis (Unitary); Yuki M Asano (University of Amsterdam); Christian Rupprecht (University of Oxford),,,Poster,,,,, Less than Few: Self-Shot Video Instance Segmentation,Pengwan Yang (University of Amsterdam)*; Yuki M Asano (University of Amsterdam); Pascal Mettes (University of Amsterdam); Cees Snoek (University of Amsterdam),,,Poster,http://arxiv.org/abs/2204.08874,,,, End-to-End Visual Editing with a Generatively Pre-Trained Artist,Andrew Brown (University of Oxford)*; Cheng-Yang Fu (Facebook.com); Omkar M Parkhi (Facebook); Tamara Berg (Facebook AI Research); Andrea Vedaldi (University of Oxford / Facebook AI Research),,,Poster,http://arxiv.org/abs/2205.01668,,,, -COUCH: Towards Controllable Human-chair Interactions,"Xiaohan Zhang (University of Tübingen, MPI Informatics); Bharat Lal Bhatnagar (University of Tübingen, MPI informatik); Sebastian Starke (University of Edinburgh); Vladimir Guzov (University of Tuebingen); Gerard Pons-Moll (University of Tübingen)*",,,Poster,http://arxiv.org/abs/2205.00541,,,, +COUCH: Towards Controllable Human-chair Interactions,"Xiaohan Zhang (University of Tübingen, MPI Informatics); Bharat Lal Bhatnagar (University of Tübingen, MPI informatik); Sebastian Starke (University of Edinburgh); Vladimir Guzov (University of Tuebingen); Gerard Pons-Moll (University of Tübingen)*",,,Poster,http://arxiv.org/abs/2205.00541,,,, MovieCuts: A New Dataset and Benchmark forCut Type Recognition,Alejandro Pardo (KAUST)*; Fabian Caba (Adobe Research); Juan C Leon (KAUST); Ali K Thabet (Facebook); Bernard Ghanem (KAUST),,,Poster,,,,, High-fidelity GAN Inversion with Padding Space,"Qingyan Bai (Tsinghua University)*; Yinghao Xu (Chinese University of Hong Kong); Jiapeng Zhu (HKUST); Weihao Xia (University College London); Yujiu Yang (Tsinghua University); Yujun Shen (Dept. of IE, CUHK)",,,Poster,http://arxiv.org/abs/2203.11105,,,, LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation,ZEYU HU (Hong Kong University of Science and Technology)*; Xuyang Bai (HKUST); Runze Zhang (Tencent); Xin Wang (Tencent); Guangyuan Sun (TENCENT); Hongbo Fu (City University of Hong Kong); Chiew-Lan Tai (Hong Kong University of Science & Technology),,,Poster,,,,, @@ -301,9 +300,9 @@ Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation,Jogendra Nath Kundu (Indian Institute of Science)*; Suvaansh Bhambri (Indian Institute of Science); Akshay R Kulkarni (Indian Institute of Science); Hiran Sarkar (Indian Institute of Science); Varun Jampani (Google); Venkatesh Babu RADHAKRISHNAN (Indian Institute of Science),,,Poster,http://arxiv.org/abs/2207.13247,,,, Designing One Unified Framework for High-Fidelity Face Reenactment and Swapping,"Chao Xu (Zhejiang University)*; Jiangning Zhang (Zhejiang University); Yue Han (Zhejiang University); Guanzhong Tian (Ningbo Research Institute, Zhejiang University); xianfang zeng (Zhejiang University); Ying Tai (Tencent YouTu); Yabiao Wang (Tencent); Chengjie Wang (Tencent; Shanghai Jiao Tong University); Yong Liu (Zhejiang University)",,,Poster,,,,, Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks,Jiehong Lin (South China University of Technology)*; Zewei Wei (South China University of Technology); Changxing Ding (South China University of Technology); Kui Jia (South China University of Technology),,,Poster,http://arxiv.org/abs/2207.05444,https://github.com/JiehongLin/Self-DPDN,,, -Intrinsic Neural Fields: Learning Functions on Manifolds,Lukas Koestler (Technical University of Munich)*; Daniel Grittner (Technische Universität München); Michael Moeller (University of Siegen); Daniel Cremers (TU Munich); Zorah Laehner (University of Siegen),,,Poster,http://arxiv.org/abs/2203.07967,,,, -LaMAR: Benchmarking Localization and Mapping for Augmented Reality,Paul-Edouard Sarlin (ETH Zurich); Mihai Dusmanu (ETH Zurich)*; Johannes L Schönberger (Microsoft); Pablo Speciale (Microsoft); Lukas Gruber (Microsoft); Viktor Larsson (Lund University); Ondrej Miksik (Microsoft); Marc Pollefeys (ETH Zurich / Microsoft),,,Poster,,,,, -3D Compositional Zero-shot Learning with DeCompositional Consensus,"Muhammad Ferjad Naeem (ETH Zürich)*; Evin Pınar Örnek (TU Munich); Yongqin Xian (ETH Zurich); Luc Van Gool (ETH Zurich); Federico Tombari (Google, TU Munich)",,,Poster,http://arxiv.org/abs/2111.14673,,,, +Intrinsic Neural Fields: Learning Functions on Manifolds,Lukas Koestler (Technical University of Munich)*; Daniel Grittner (Technische Universität München); Michael Moeller (University of Siegen); Daniel Cremers (TU Munich); Zorah Laehner (University of Siegen),,,Poster,http://arxiv.org/abs/2203.07967,,,, +LaMAR: Benchmarking Localization and Mapping for Augmented Reality,Paul-Edouard Sarlin (ETH Zurich); Mihai Dusmanu (ETH Zurich)*; Johannes L Schönberger (Microsoft); Pablo Speciale (Microsoft); Lukas Gruber (Microsoft); Viktor Larsson (Lund University); Ondrej Miksik (Microsoft); Marc Pollefeys (ETH Zurich / Microsoft),,,Poster,,,,, +3D Compositional Zero-shot Learning with DeCompositional Consensus,"Muhammad Ferjad Naeem (ETH Zürich)*; Evin Pınar Örnek (TU Munich); Yongqin Xian (ETH Zurich); Luc Van Gool (ETH Zurich); Federico Tombari (Google, TU Munich)",,,Poster,http://arxiv.org/abs/2111.14673,,,, Video Mask Transfiner for High-Quality Video Instance Segmentation,Lei Ke (HKUST)*; Henghui Ding (ETH Zurich); Martin Danelljan (ETH Zurich); Yu-Wing Tai (Kuaishou Technology / HKUST); Chi-Keung Tang (Hong Kong University of Science and Technology); Fisher Yu (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.14012,,,, FashionViL: Fashion-Focused Vision-and-Language Representation Learning,Xiao Han (University of Surrey)*; Licheng Yu (Facebook); Xiatian Zhu (University of Surrey); Li Zhang (Fudan University); Yi-Zhe Song (University of Surrey); Tao Xiang (University of Surrey),,,Poster,http://arxiv.org/abs/2207.08150,https://github.com/BrandonHanx/mmf,,, Adaptive Face Forgery Detection in Cross Domain,Luchuan Song (University of Science and Technology of China)*; Zheng Fang (BeihangUniversity); Xiaodan Li (Alibaba Group); Xiaoyi Dong (University of Science and Technology of China); Zhenchao Jin (University of Science and Technology of China); Yuefeng Chen (Alibaba Group); Siwei Lyu (University at Buffalo),,,Poster,,,,, @@ -329,8 +328,8 @@ Automatic dense annotation of large-vocabulary sign language videos,"Liliane Mom Few-shot Class-incremental Learning via Entropy-regularized Data-free Replay,Huan Liu (McMaster University)*; Li Gu (Huawei Canada); Zhixiang Chi (Huawei Noah's Ark Laboratory); Yuanhao Yu (Huawei Noah's Ark Laboratory); Yang Wang (Concordia University); Jun Chen (McMaster University); Jin Tang ( Huawei Noah's Ark Laboratory),,,Poster,http://arxiv.org/abs/2207.11213,,,, Learning Instance-Specific Adaptation for Cross-Domain Segmentation,Yuliang Zou (Virginia Tech)*; Zizhao Zhang (Google); Chun-Liang Li (Google); Han Zhang (Google); Tomas Pfister (Google); Jia-Bin Huang (Facebook ),,,Poster,http://arxiv.org/abs/2203.16530,,,, SALVe: Semantic Alignment Verification for Floorplan Reconstruction from Sparse Panoramas,"John W Lambert (Georgia Institute of Technology)*; Yuguang Li (Zillow Group); Ivaylo Boyadzhiev (Zillow Group); Lambert Wixson (Zillow Group); Manjunath Narayana (Zillow group); Will A Hutchcroft (Zillow Group); James Hays (Georgia Institute of Technology, USA); Frank Dellaert (Georgia Tech); Sing Bing Kang (Zillow Group)",,,Poster,,,,, -Active Learning Strategies for Weakly-Supervised Object Detection,Huy V. Vo (Ecole Normale Supérieure - INRIA - Valeo.ai)*; Oriane Siméoni (valeo.ai); Spyros Gidaris (valeo.ai); Andrei Bursuc (valeo.ai); Patrick Pérez (Valeo.ai); Jean Ponce (Inria),,,Poster,http://arxiv.org/abs/2207.12112,https://github.com/huyvvo/BiB,,, -3D Human Pose Estimation Using Möbius Graph Convolutional Networks,Niloofar Azizi (ICG department of TU Graz)*; Horst Possegger (Graz University of Technology); Emanuele Rodola (Sapienza University of Rome); Horst Bischof (Graz University of Technology),,,Poster,,,,, +Active Learning Strategies for Weakly-Supervised Object Detection,Huy V. Vo (Ecole Normale Supérieure - INRIA - Valeo.ai)*; Oriane Siméoni (valeo.ai); Spyros Gidaris (valeo.ai); Andrei Bursuc (valeo.ai); Patrick Pérez (Valeo.ai); Jean Ponce (Inria),,,Poster,http://arxiv.org/abs/2207.12112,https://github.com/huyvvo/BiB,,, +3D Human Pose Estimation Using Möbius Graph Convolutional Networks,Niloofar Azizi (ICG department of TU Graz)*; Horst Possegger (Graz University of Technology); Emanuele Rodola (Sapienza University of Rome); Horst Bischof (Graz University of Technology),,,Poster,,,,, Real-time Online Video Detection with Temporal Smoothing Transformers,Yue Zhao (University of Texas at Austin)*; Philipp Kraehenbuehl (UT Austin),,,Poster,,,,, 3D-FM GAN: Towards 3D-Controllable Face Manipulation,Yuchen Liu (Princeton University)*; Zhixin Shu (Adobe Research); Yijun Li (Adobe Research); Zhe Lin (Adobe Research); Richard Zhang (Adobe); Sun-Yuan Kung (Princeton University),,,Poster,http://arxiv.org/abs/2208.11257,,,, SinNeRF: Training Neural Radiance Field on Complex Scene from a Single Image,Dejia Xu (University of Texas at Austin)*; Yifan Jiang (University of Texas at Austin); Peihao Wang (University of Texas at Austin); Zhiwen Fan (University of Texas at Austin); Humphrey Shi (U of Oregon | UIUC | PAIR); Zhangyang Wang (University of Texas at Austin),,,Poster,,,,, @@ -339,7 +338,7 @@ Identity-aware Hand Mesh Estimation and Personalization from RGB Images,"Deying TALLFormer: Temporal Action Localization with a Long-memory Transformer,Feng Cheng (University of North Carolina ch); Gedas Bertasius (UNC Chapel Hill)*,,,Poster,http://arxiv.org/abs/2204.01680,https://github.com/klauscc/TALLFormer,,, Unsupervised and Semi-supervised Bias Benchmarking in Face Recognition,Siqi Deng (Amazon)*; Alexandra Chouldechova (CMU); Yongxin Wang (Amazon); Wei Xia (Amazon); Pietro Perona (California Institute of Technology),,,Poster,,,,, Domain Adaptive Hand Keypoint and Pixel Localization in the Wild,Takehiko Ohkawa (The University of Tokyo)*; Yu-Jhe Li (Carnegie Mellon University); Qichen Fu (Carnegie Mellon University); Ryosuke Furuta (The University of Tokyo); Kris Kitani (Carnegie Mellon University); Yoichi Sato (University of Tokyo),,,Poster,http://arxiv.org/abs/2203.08344,,,, -Skeleton-free Pose Transfer for Stylized 3D Characters,Zhouyingcheng Liao (Saarland University)*; Jimei Yang (Adobe); Jun Saito (Adobe); Gerard Pons-Moll (University of Tübingen); Yang Zhou (Adobe Research),,,Poster,http://arxiv.org/abs/2208.00790,,,, +Skeleton-free Pose Transfer for Stylized 3D Characters,Zhouyingcheng Liao (Saarland University)*; Jimei Yang (Adobe); Jun Saito (Adobe); Gerard Pons-Moll (University of Tübingen); Yang Zhou (Adobe Research),,,Poster,http://arxiv.org/abs/2208.00790,,,, Differentiable Raycasting for Self-supervised Occupancy Forecasting,Tarasha Khurana (Carnegie Mellon University)*; Peiyun Hu (Carnegie Mellon University); Achal D Dave (Amazon); Jason P Ziglar (Argo AI); David Held (); Deva Ramanan (Carnegie Mellon University),,,Poster,,,,, InAction: Interpretable Action Decision Making for Autonomous Driving,Taotao Jing (Tulane University)*; Haifeng Xia (Tulane University); Renran Tian (Indiana University-Purdue University Indianapolis); Haoran Ding (IUPUI); Xiao Luo (IUPUI); Joshua E Domeyer (Toyota Motor North America); Rini Sherony (Toyota CSRC); Zhengming Ding (Tulane University),,,Poster,,,,, CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection,Jyh-Jing Hwang (Waymo)*; Henrik Kretzschmar (Waymo); Joshua M Manela (Waymo); Sean Rafferty (Waymo); Nicholas Armstrong-Crews (Waymo); Tiffany Chen (Waymo); Dragomir Anguelov (Waymo),,,Poster,,,,, @@ -374,18 +373,18 @@ DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation,R Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretraining,Qihang Zhang (Chinese University of Hong Kong); Zhenghao Peng (Chinese University of Hong Kong); Bolei Zhou (UCLA)*,,,Poster,http://arxiv.org/abs/2204.02393,,,, Multi-Curve Translator for High-Resolution Photorealistic Image Translation,Yuda Song (Zhejiang University); Hui Qian (Zhejiang University); Xin Du (Zhejiang University)*,,,Poster,http://arxiv.org/abs/2203.07756,,,, Dynamic Metric Learning with Cross-Level Concept Distillation,Wenzhao Zheng (Tsinghua University)*; Yuanhui Huang (Tsinghua University); Borui Zhang (Tsinghua University); Jie Zhou (Tsinghua University); Jiwen Lu (Tsinghua University),,,Poster,,,,, -Deep Bayesian Video Frame Interpolation,"Zhiyang Yu (Harbin Institute of Technology)*; Yu Zhang (Beihang University); Xujie Xiang (Beihang University); Dongqing Zou (SenseTime Research；Qing Yuan Research Institute, Shanghai Jiao Tong University); Xijun Chen (Harbin Institute of Technology); Jimmy Ren (SenseTime Research;Qing Yuan Research Institute, Shanghai Jiao Tong University)",,,Poster,,,,, -PanoFormer: Panorama Transformer for Indoor 360° Depth Estimation,Zhijie Shen (Beijing Jiaotong University); Chunyu Lin (Beijing Jiaotong University)*; Kang Liao (Beijing Jiaotong University); Lang Nie (Beijing Jiaotong University); Zishuo Zheng (Beijing Jiaotong University); Yao Zhao (Beijing Jiaotong University),,,Poster,,,,, +Deep Bayesian Video Frame Interpolation,"Zhiyang Yu (Harbin Institute of Technology)*; Yu Zhang (Beihang University); Xujie Xiang (Beihang University); Dongqing Zou (SenseTime Researchï¼›Qing Yuan Research Institute, Shanghai Jiao Tong University); Xijun Chen (Harbin Institute of Technology); Jimmy Ren (SenseTime Research;Qing Yuan Research Institute, Shanghai Jiao Tong University)",,,Poster,,,,, +PanoFormer: Panorama Transformer for Indoor 360° Depth Estimation,Zhijie Shen (Beijing Jiaotong University); Chunyu Lin (Beijing Jiaotong University)*; Kang Liao (Beijing Jiaotong University); Lang Nie (Beijing Jiaotong University); Zishuo Zheng (Beijing Jiaotong University); Yao Zhao (Beijing Jiaotong University),,,Poster,,,,, Cross Attention Based Style Distribution for Controllable Person Image Synthesis,Xinyue Zhou (East China Normal University ); Mingyu Yin (East China Normal University); Xinyuan Chen (Shanghai AI Laboratory); Li Sun (East China Normal University)*; Changxin Gao (Huazhong University of Science and Technology); Qingli Li (East China Normal University),,,Poster,http://arxiv.org/abs/2208.00712,,,, Generative Meta-Adversarial Network for Unseen Object Navigation,"Sixian Zhang (ICT, China Academy of Science)*; Weijie Li (ICT, China Academy of Sciences); Xinhang Song (ICT); Yubing Bai (ICT,China Academy of Science); Shuqiang Jiang (ICT, China Academy of Science)",,,Poster,,,,, Unsupervised Visual Representation Learning by Synchronous Momentum Grouping,Bo Pang (Shanghai Jiao Tong University)*; Yifan Zhang (Shanghai Jiao Tong University); Yaoyi Li (Huawei); Jia Cai (Huawei); Cewu Lu (Shanghai Jiao Tong University),,,Poster,http://arxiv.org/abs/2207.06167,,,, -OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers,Jialun Pei (Huazhong University of Science and Technology); Tianyang Cheng (Huazhong University of Science and Technology); Deng-Ping Fan (ETH Zurich)*; He Tang (Huazhong University of Science and Technology); Chuanbo Chen (Huazhong University of Science and Technology); Luc Van Gool (ETH Zürich),,,Poster,http://arxiv.org/abs/2207.02255,https://github.com/PJLallen/OSFormer,,, -Highly Accurate Dichotomous Image Segmentation,Xuebin Qin (University of Alberta); Hang Dai (Mohamed bin Zayed University of Artificial Intelligence); Xiaobin Hu (Technische Universität München); Deng-Ping Fan (ETH Zurich)*; Ling Shao (Terminus Group); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2203.03041,,,, -KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints,Marko Mihajlovic (ETH Zurich)*; Aayush Bansal (Carnegie Mellon University); Michael Zollhöfer (Facebook Reality Labs); Siyu Tang (ETH Zurich); Shunsuke Saito (Facebook),,,Poster,http://arxiv.org/abs/2205.04992,,,, +OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers,Jialun Pei (Huazhong University of Science and Technology); Tianyang Cheng (Huazhong University of Science and Technology); Deng-Ping Fan (ETH Zurich)*; He Tang (Huazhong University of Science and Technology); Chuanbo Chen (Huazhong University of Science and Technology); Luc Van Gool (ETH Zürich),,,Poster,http://arxiv.org/abs/2207.02255,https://github.com/PJLallen/OSFormer,,, +Highly Accurate Dichotomous Image Segmentation,Xuebin Qin (University of Alberta); Hang Dai (Mohamed bin Zayed University of Artificial Intelligence); Xiaobin Hu (Technische Universität München); Deng-Ping Fan (ETH Zurich)*; Ling Shao (Terminus Group); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2203.03041,,,, +KeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of Keypoints,Marko Mihajlovic (ETH Zurich)*; Aayush Bansal (Carnegie Mellon University); Michael Zollhöfer (Facebook Reality Labs); Siyu Tang (ETH Zurich); Shunsuke Saito (Facebook),,,Poster,http://arxiv.org/abs/2205.04992,,,, MENet: a Memory-Based Network with Dual-Branch for Efficient Event Stream Processing,"Linhui Sun (CASIA)*; Yifan Zhang (Institute of Automation, Chinese Academy of Sciences); Ke Cheng (Institute of Automation, Chinese Academy of Sciences); Jian Cheng (""Chinese Academy of Sciences, China""); Hanqing Lu (NLPR, Institute of Automation, CAS)",,,Poster,,,,, Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals,Simon Vandenhende (KU Leuven)*; Dhruv Mahajan (Facebook); Filip Radenovic (Facebook AI); Deepti Ghadiyaram (Facebook),,,Poster,http://arxiv.org/abs/2203.12892,https://github.com/facebookresearch/visual-counterfactuals,,, LEDNet: Joint Low-light Enhancement and Deblurring in the Dark,Shangchen Zhou (Nanyang Technological University)*; Chongyi Li ( Nanyang Technological University); Chen Change Loy (Nanyang Technological University),,,Poster,http://arxiv.org/abs/2202.03373,,,, -RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering,Di Chang (Technical University of Munich)*; Aljaz Bozic (Technical University Munich); Tong Zhang (EPFL); Qingsong Yan (hong kong university of science and technology); Yingcong Chen (Hong Kong University of Science and Technology); Sabine Süsstrunk (EPFL); Matthias Niessner (Technical University of Munich),,,Poster,,,,, +RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering,Di Chang (Technical University of Munich)*; Aljaz Bozic (Technical University Munich); Tong Zhang (EPFL); Qingsong Yan (hong kong university of science and technology); Yingcong Chen (Hong Kong University of Science and Technology); Sabine Süsstrunk (EPFL); Matthias Niessner (Technical University of Munich),,,Poster,,,,, StretchBEV: Stretching Future Instance Prediction Spatially and Temporally,Kaan Adil Akan (Koc University); Fatma Guney (Koc University)*,,,Poster,http://arxiv.org/abs/2203.13641,,,, AgeTransGAN for Facial Age Transformation with Rectified Performance Metrics,Gee-Sern Hsu (National Taiwan University of Science and Technology)*; Rui-Cang Xie ( National Taiwan University of Science and Technology); Zhi-Ting Chen (National Taiwan University of Science and Technology); Yu-Hong Lin (National Taiwan University of Science and Technology),,,Poster,,,,, Boosting Supervised Dehazing Methods via Bi-level Patch Reweighting,Xingyu Jiang (beihang ); Hongkun Dou (Beihang University); Chengwei Fu (beihang); Bingquan Dai (Beihang); Tianrun Xu (North China University of Technology); Yue Deng (Samsung Research America)*,,,Poster,,,,, @@ -405,16 +404,16 @@ Improving Few-Shot Part Segmentation using Coarse Supervision,"Oindrila Saha (Un Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation,Guolei Sun (ETH Zurich); Yun Liu (ETH Zurich)*; Hao Tang (ETH Zurich); Ajad Chhatkuli (ETH Zurich); Le Zhang (University of Electronic Science and Technology of China); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.10436,https://github.com/GuoleiSun/VSS-MRCFA,,, Out-of-distribution Detection with Boundary Aware Learning,"Sen Pei (Institute of Automation, Chinese Academy of Sciences)*; Xin Zhang (Institute of Automation, Chinese Academy of Sciences, University of Chinese Academy of Sciences); Bin Fan (University of Science and Technology Beijing); Gaofeng Meng (Chinese Academy of Sciences)",,,Poster,http://arxiv.org/abs/2112.11648,,,, NeILF: Neural Incident Light Field for Physically-based Material Estimation,Yao Yao (Apple Inc.); Jingyang Zhang (The Hong Kong University of Science and Technology)*; Jingbo Liu (Apple Inc.); Yihang Qu (Apple Inc.); Tian Fang (Apple); David N McKinnon (Apple); Yanghai Tsin (Apple Inc); Long Quan (Apple),,,Poster,http://arxiv.org/abs/2203.07182,,,, -ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers,Jonáš Kulhánek (Czech Technical University in Prague)*; Erik Derner (CTU CIIRC); Torsten Sattler (Czech Technical University in Prague); Robert Babuska (TU Delft),,,Poster,http://arxiv.org/abs/2203.10157,,,, +ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers,Jonáš Kulhánek (Czech Technical University in Prague)*; Erik Derner (CTU CIIRC); Torsten Sattler (Czech Technical University in Prague); Robert Babuska (TU Delft),,,Poster,http://arxiv.org/abs/2203.10157,,,, L-Tracing: Fast Light Visibility Estimation on Neural Surfaces by Sphere Tracing,Ziyu Chen (Shanghai Jiao Tong University)*; Chenjing Ding (Sensetime Group Limited); Jianfei Guo (Shanghai AI Laboratory); Dongliang Wang (SenseTime Group Limited); Yikang Li (Shanghai AI Lab); Xuan Xiao (SenseTime Group Limited); Wei Wu (SenseTime Group Limited); Li Song (Shanghai Jiao Tong University),,,Poster,,,,, ARF: Artistic Radiance fields,"Kai Zhang (Cornell University)*; Nicholas I Kolkin (Adobe Research); Sai Bi (Adobe Research); Fujun Luan (Adobe Research); Zexiang Xu (Adobe Research); Eli Shechtman (Adobe Research, US); Noah Snavely (Cornell University and Google AI)",,,Poster,http://arxiv.org/abs/2206.06360,,,, Multiview Stereo with Cascaded Epipolar RAFT,Zeyu Ma (Princeton University)*; Zachary Teed (Princeton University); Jia Deng (Princeton University),,,Poster,http://arxiv.org/abs/2205.04502,https://github.com/princeton-vl/CER-MVS,,, What to Hide from Your Students: Attention-Guided Masked Image Modeling,"Ioannis Kakogeorgiou (National Technical University of Athens)*; Spyros Gidaris (valeo.ai); Bill Psomas (National Technical University of Athens); Yannis Avrithis (IARAI, Athena RC); Andrei Bursuc (valeo.ai); Konstantinos Karantzalos (National Technical University of Athens); Nikos Komodakis (University of Crete)",,,Poster,http://arxiv.org/abs/2203.12719,https://github.com/gkakogeorgiou/attmask,,, Static and Dynamic Concepts for Self-supervised Video Representation Learning,Rui Qian (The Chinese University of Hong Kong)*; Shuangrui Ding (Shanghai Jiao Tong University); Xian Liu (The Chinese University of Hong Kong); Dahua Lin (The Chinese University of Hong Kong),,,Poster,http://arxiv.org/abs/2207.12795,,,, -Deep Partial Updating: Towards Communication Efficient Updating for On-device Inference,Zhongnan Qu (ETH Zurich)*; Cong Liu (University of Texas at Dallas); Lothar Thiele (ETH Zürich),,,Poster,http://arxiv.org/abs/2007.03071,,,, +Deep Partial Updating: Towards Communication Efficient Updating for On-device Inference,Zhongnan Qu (ETH Zurich)*; Cong Liu (University of Texas at Dallas); Lothar Thiele (ETH Zürich),,,Poster,http://arxiv.org/abs/2007.03071,,,, Gradient-based Uncertainty for Monocular Depth Estimation,Julia Hornauer (Ulm University)*; Vasileios Belagiannis (Otto von Guericke University Magdeburg),,,Poster,http://arxiv.org/abs/2208.02005,https://github.com/jhornauer/GrUMoDepth,,, Flow-Guided Transformer for Video Inpainting,Kaidong Zhang (University of Science and Technology of China); Jingjing Fu (Microsoft)*; Dong Liu (University of Science and Technology of China),,,Poster,http://arxiv.org/abs/2208.06768,https://github.com/hitachinsk/FGT,,, -Relationformer: A Unified Framework for Image-to-Graph Generation,Suprosanna Shit (TUM)*; Rajat Koner (Ludwig Maximilian University of Munich); Bastian Wittmann (Technical University of Munich); Johannes C. Paetzold (TUM); Ivan Ezhov (TUM); Hongwei Li (Technical University of Munich); Jiazhen Pan (Technical University of Munich); Sahand Sharifzadeh (Ludwig Maximilian University of Munich); Georgios Kaissis (Technische Universität München); Volker Tresp (LMU); Bjoern Menze (TUM),,,Poster,http://arxiv.org/abs/2203.10202,,,, +Relationformer: A Unified Framework for Image-to-Graph Generation,Suprosanna Shit (TUM)*; Rajat Koner (Ludwig Maximilian University of Munich); Bastian Wittmann (Technical University of Munich); Johannes C. Paetzold (TUM); Ivan Ezhov (TUM); Hongwei Li (Technical University of Munich); Jiazhen Pan (Technical University of Munich); Sahand Sharifzadeh (Ludwig Maximilian University of Munich); Georgios Kaissis (Technische Universität München); Volker Tresp (LMU); Bjoern Menze (TUM),,,Poster,http://arxiv.org/abs/2203.10202,,,, ARAH: Animatable Volume Rendering of Articulated Human SDFs,Shaofei wang (ETH Zurich)*; Katja Schwarz (MPI Tuebingen); Andreas Geiger (University of Tuebingen); Siyu Tang (ETH Zurich),,,Poster,,,,, Learning Hierarchy Aware Features for Reducing Mistake Severity,Ashima Garg (IIIT Delhi)*; Depanshu Sani (Indraprastha Institute of Information Technology); Saket Anand (Indraprastha Institute of Information Technology Delhi),,,Poster,http://arxiv.org/abs/2207.12646,https://github.com/07Agarg/HAF,,, Exploiting Unlabeled Data with Vision and Language Models for Object Detection,Shiyu Zhao (Rutgers University)*; Zhixing Zhang (Rutgers University); Samuel Schulter (NEC Laboratories America); Long Zhao (Google Research); Vijay Kumar B G (NEC Laboratories America); Anastasis Stathopoulos (Rutgers University); Manmohan Chandraker (UC San Diego); Dimitris N. Metaxas (Rutgers),,,Poster,http://arxiv.org/abs/2207.08954,https://github.com/xiaofeng94/VL-PLM,,, @@ -446,7 +445,7 @@ Patch Similarity Aware Data-Free Quantization for Vision Transformers,"Zhikai Li Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution,"Yuehan Zhang (National University of Singapore)*; Bo Ji (National University of Singapore); Jia Hao (HiSilicon (Shanghai) Technologies Co., Ltd); Angela Yao (National University of Singapore)",,,Poster,http://arxiv.org/abs/2208.03324,https://github.com/Yuehan717/PDASR,,, DualFormer: Local-Global Stratified Transformer for Efficient Video Recognition,Yuxuan Liang (National University of Singapore)*; Pan Zhou (Sea AI Lab); Roger Zimmermann (NUS); Shuicheng Yan (Sea AI Labs),,,Poster,http://arxiv.org/abs/2112.04674,https://github.com/sail-sg/dualformer,,, Hierarchical Contrastive Inconsistency Learning for Deepfake Video Detection,Zhihao Gu (Shanghai Jiao Tong University)*; Taiping Yao (Tencent YouTu); Yang Chen (Tencent); Shouhong Ding (Tencent); Lizhuang Ma (Shanghai Jiao Tong University),,,Poster,,,,, -Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal,Xinwei Liu (Institute of Information Engineering，Chinese Academy of Sciences)*; Jian Liu (Ant Group); Yang Bai (Tsinghua); Jindong Gu (University of Munich); Tao Chen (Ant Group); Xiaojun Jia (Institute of Information Engineering，Chinese Academy of Sciences); Xiaochun Cao (Sun Yat-sen University),,,Poster,http://arxiv.org/abs/2207.08178,,,, +Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal,Xinwei Liu (Institute of Information Engineering，Chinese Academy of Sciences)*; Jian Liu (Ant Group); Yang Bai (Tsinghua); Jindong Gu (University of Munich); Tao Chen (Ant Group); Xiaojun Jia (Institute of Information Engineering，Chinese Academy of Sciences); Xiaochun Cao (Sun Yat-sen University),,,Poster,http://arxiv.org/abs/2207.08178,,,, ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO,Sanghyuk Chun (NAVER AI Lab)*; Wonjae Kim (NAVER AI Lab); Song Park (NAVER AI Lab); Minsuk Chang (NAVER AI Lab); Seong Joon Oh (Naver AI Lab),,,Poster,http://arxiv.org/abs/2204.03359,https://github.com/naver-ai/eccv-caption,,, Personalizing Federated Medical Image Segmentation via Local Calibration,Jiacheng Wang (Xiamen University); Yueming Jin (The Chinese University of Hong Kong); Liansheng Wang (Xiamen University)*,,,Poster,http://arxiv.org/abs/2207.04655,https://github.com/jcwang123/FedLC,,, Learning to Detect Every Thing in an Open World,Kuniaki Saito (Boston University)*; Ping Hu (Boston University); Trevor Darrell (UC Berkeley); Kate Saenko (Boston University),,,Poster,http://arxiv.org/abs/2112.01698,,,, @@ -480,28 +479,28 @@ MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Eff Neural Density-Distance Fields,Itsuki UEDA (University of Tsukuba)*; Yoshihiro Fukuhara (Waseda University); Hirokatsu Kataoka (National Institute of Advanced Industrial Science and Technology (AIST)); Hiroaki Aizawa (Hiroshima University); Hidehiko Shishido (University of Tsukuba); Itaru Kitahara (University of Tsukuba),,,Poster,http://arxiv.org/abs/2207.14455,https://github.com/ueda0319/neddf,,, MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents,Eun Sun Lee (Seoul National University)*; Junho Kim (Seoul National University); Sangwon Park (Seoul Nat'l University); Young Min Kim (Seoul National University),,,Poster,,,,, "L3: Accelerator-Friendly Lossless Image Format for High-Resolution, High-Throughput DNN Training",Jonghyun Bae (Seoul National University)*; Woohyeon Baek (Seoul National University); Tae Jun Ham (Seoul National University); Jae W. Lee (Seoul National University),,,Poster,http://arxiv.org/abs/2208.08711,,,, -Prior-Guided Adversarial Initialization for Fast Adversarial Training,"Xiaojun Jia (Institute of Information Engineering，Chinese Academy of Sciences)*; Yong Zhang (Tencent AI Lab); Xingxing Wei (Beihang University); Baoyuan Wu (The Chinese University of Hong Kong, Shenzhen; Shenzhen Research Institute of Big Data); Ke Ma (UCAS); Jue Wang (Tencent AI Lab); Xiaochun Cao (Sun Yat-sen University)",,,Poster,http://arxiv.org/abs/2207.08859,https://github.com/jiaxiaojunQAQ/FGSM-PGI,,, +Prior-Guided Adversarial Initialization for Fast Adversarial Training,"Xiaojun Jia (Institute of Information Engineering，Chinese Academy of Sciences)*; Yong Zhang (Tencent AI Lab); Xingxing Wei (Beihang University); Baoyuan Wu (The Chinese University of Hong Kong, Shenzhen; Shenzhen Research Institute of Big Data); Ke Ma (UCAS); Jue Wang (Tencent AI Lab); Xiaochun Cao (Sun Yat-sen University)",,,Poster,http://arxiv.org/abs/2207.08859,https://github.com/jiaxiaojunQAQ/FGSM-PGI,,, Housekeep: Tidying Virtual Households using Commonsense Reasoning,Yash Mukund Kant (University of Toronto)*; Arun Ramachandran (Georgia Institute of Technology); Sriram Yenamandra (Georgia Institute of Technology); Igor Gilitschenski (University of Toronto); Dhruv Batra (Georgia Tech & Facebook AI Research); Andrew Szot (Georgia Institute of Technology); Harsh Agrawal (Georgia Institute of Technology),,,Poster,http://arxiv.org/abs/2205.10712,,,, Real-RawVSR: Real-World Raw Video Super-Resolution with a Benchmark Dataset,Huanjing Yue (Tianjin University)*; Zhiming Zhang (Tianjin University); Jingyu Yang (Tianjin University),,,Poster,,,,, ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning,Shengchao Hu (Shanghai Jiao Tong University)*; Li Chen (Shanghai AI Laboratory); Penghao Wu (Shanghai Jiao Tong University); Hongyang Li (SenseTime); Junchi Yan (Shanghai Jiao Tong University); Dacheng Tao (JD.com),,,Poster,,,,, NeXT: Towards High Quality Neural Radiance Fields via Multi-Skip Transformer,Yunxiao Wang (Tsinghua University); Yanjie Li (Tsinghua University)*; Peidong Liu (Tsinghua University); Tao Dai (Shenzhen University); Shu-Tao Xia (Tsinghua University),,,Poster,,,,, Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution,Zhongwei Qiu (University of Science and Technology Beijing); Huan Yang (Microsoft Research)*; Jianlong Fu (Microsoft Research); Dongmei Fu (University of Science and Technology Beijing),,,Poster,http://arxiv.org/abs/2208.03012,https://github.com/researchmm/FTVSR,,, Adversarial Partial Domain Adaptation by Cycle Inconsistency,"Kun-Yu Lin (Sun Yat-sen University); Jiaming Zhou (Sun Yat-sen University); Yukun Qiu (Sun Yat-sen University); WEI-SHI ZHENG (Sun Yat-sen University, China)*",,,Poster,,,,, -BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks,Uddeshya Upadhyay (University of Tübingen)*; Shyamgopal Karthik (University of Tübingen); Massimiliano Mancini (University of Tübingen); Yanbei Chen (University of Tübingen); Zeynep Akata (University of Tübingen),,,Poster,http://arxiv.org/abs/2207.06873,https://github.com/ExplainableML/BayesCap,,, +BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks,Uddeshya Upadhyay (University of Tübingen)*; Shyamgopal Karthik (University of Tübingen); Massimiliano Mancini (University of Tübingen); Yanbei Chen (University of Tübingen); Zeynep Akata (University of Tübingen),,,Poster,http://arxiv.org/abs/2207.06873,https://github.com/ExplainableML/BayesCap,,, Domain Randomization-Enhanced Depth Simulation and Restoration for Perceiving and Grasping Specular and Transparent Objects,Qiyu Dai (Peking University); Jiyao Zhang (Xi'an Jiaotong University); Qiwei Li (Peking University); tianhao wu (Peking University); Hao Dong (Peking University); Ziyuan Liu (Huawei group); Ping Tan (Simon Fraser University); He Wang (Peking University)*,,,Poster,http://arxiv.org/abs/2208.03792,https://github.com/PKU-EPIC/DREDS,,, PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo,"Wenqi Yang (The University of Hong Kong)*; Guanying CHEN (The Chinese University of Hong Kong, Shenzhen); Chaofeng Chen (Nanyang Technological University); Zhenfang Chen (MIT-IBM Watson AI Lab); Kwan-Yee K. Wong (The University of Hong Kong)",,,Poster,,,,, -DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation,Ailing Zeng (The Chinese University of Hong Kong)*; Xuan Ju (The Chinese University of Hong Kong); Lei Yang (Sensetime Group Limited); Ruiyuan Gao (The Chinese University of Hong Kong); Xizhou Zhu (SenseTime); Bo Dai (Shanghai AI Lab); Qiang Xu (The Chinese University of Hong Kong),,,Poster,,https://github.com/cure-lab/DeciWatch,,, +DeciWatch: A Simple Baseline for 10× Efficient 2D and 3D Pose Estimation,Ailing Zeng (The Chinese University of Hong Kong)*; Xuan Ju (The Chinese University of Hong Kong); Lei Yang (Sensetime Group Limited); Ruiyuan Gao (The Chinese University of Hong Kong); Xizhou Zhu (SenseTime); Bo Dai (Shanghai AI Lab); Qiang Xu (The Chinese University of Hong Kong),,,Poster,,https://github.com/cure-lab/DeciWatch,,, Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting,Dooseop Choi (ETRI)*; KyoungWook Min (ETRI),,,Poster,http://arxiv.org/abs/2207.04624,https://github.com/d1024choi/HLSTrajForecast,,, SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos,Ailing Zeng (The Chinese University of Hong Kong)*; Lei Yang (Sensetime Group Limited); Xuan Ju (The Chinese University of Hong Kong); Jiefeng Li (Shanghai Jiao Tong University); Jianyi Wang (Nanyang Technological University); Qiang Xu (The Chinese University of Hong Kong),,,Poster,http://arxiv.org/abs/2112.13715,https://github.com/cure-lab/SmoothNet,,, -Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency,Tom Monnier (École des ponts Paristech)*; Matthew Fisher (Adobe Research); Alexei A Efros (UC Berkeley); Mathieu Aubry (École des ponts ParisTech),,,Poster,http://arxiv.org/abs/2204.10310,,,, -End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution,"Mingxiang Liao (University of Chinese Academy of Sciences); Fang Wan (University of Chinese Academy of Sciences)*; Yuan Yao (University of Chinese Academy of Sciences); Zhenjun Han (University of Chinese Academy of Sciences); Zou Jialing (University of Chinese Academy of Science); Yuze Wang ( Huawei Noah’s Ark Lab); Bailan Feng (Huawei Noah's Ark Lab); Peng Yuan (Huawei Noah’s Ark Lab); Qixiang Ye (University of Chinese Academy of Sciences, China)",,,Poster,,,,, +Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency,Tom Monnier (École des ponts Paristech)*; Matthew Fisher (Adobe Research); Alexei A Efros (UC Berkeley); Mathieu Aubry (École des ponts ParisTech),,,Poster,http://arxiv.org/abs/2204.10310,,,, +End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution,"Mingxiang Liao (University of Chinese Academy of Sciences); Fang Wan (University of Chinese Academy of Sciences)*; Yuan Yao (University of Chinese Academy of Sciences); Zhenjun Han (University of Chinese Academy of Sciences); Zou Jialing (University of Chinese Academy of Science); Yuze Wang ( Huawei Noah’s Ark Lab); Bailan Feng (Huawei Noah's Ark Lab); Peng Yuan (Huawei Noah’s Ark Lab); Qixiang Ye (University of Chinese Academy of Sciences, China)",,,Poster,,,,, PAC-Net: Highlight Your Video via History Preference Modeling,Hang Wang (Huawei HiSilicon)*; Penghao Zhou (ByteDance); Chong Zhou (Nanyang Technological University); Zhao Zhang (Nankai University); Xing Sun (Shopee),,,Poster,,,,, Efficient Point Cloud Analysis Using Hilbert Curve,Wanli Chen (CUHK)*; Xinge Zhu (The Chinese University of Hong Kong); Guojin Chen (The Chinese University of Hong Kong); Bei Yu (CUHK),,,Poster,,,,, -Learning Online Multi-Sensor Depth Fusion,Erik Sandström (ETH Zürich)*; Martin R. Oswald (ETH Zurich); Suryansh Kumar (ETH Zurich); Silvan Weder (ETH Zürich); Fisher Yu (ETH Zurich); Cristian Sminchisescu (Lund University); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2204.03353,,,, +Learning Online Multi-Sensor Depth Fusion,Erik Sandström (ETH Zürich)*; Martin R. Oswald (ETH Zurich); Suryansh Kumar (ETH Zurich); Silvan Weder (ETH Zürich); Fisher Yu (ETH Zurich); Cristian Sminchisescu (Lund University); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2204.03353,,,, Self-Support Few-Shot Semantic Segmentation,"Qi Fan (HKUST)*; Wenjie Pei (Harbin Institute of Technology, Shenzhen); Yu-Wing Tai (Kuaishou Technology / HKUST); Chi-Keung Tang (Hong Kong University of Science and Technology)",,,Poster,http://arxiv.org/abs/2207.11549,https://github.com/fanq15/SSP,,, Few-Shot Object Detection with Model Calibration,Qi Fan (HKUST)*; Chi-Keung Tang (Hong Kong University of Science and Technology); Yu-Wing Tai (Kuaishou Technology / HKUST),,,Poster,,,,, S2-VER: Semi-Supervised Visual Emotion Recognition,Guoli Jia (NanKai University); Jufeng Yang (Nankai University )*,,,Poster,,,,, -Self-Supervision Can Be a Good Few-Shot Learner,"Yuning Lu (USTC); liangjian Wen (the Noah’s Ark Lab, Huawei Technologies Company Limited); Jianzhuang Liu (Huawei Noah's Ark Lab); Yajing Liu (USTC); Xinmei Tian (USTC)*",,,Poster,http://arxiv.org/abs/2207.09176,,,, +Self-Supervision Can Be a Good Few-Shot Learner,"Yuning Lu (USTC); liangjian Wen (the Noah’s Ark Lab, Huawei Technologies Company Limited); Jianzhuang Liu (Huawei Noah's Ark Lab); Yajing Liu (USTC); Xinmei Tian (USTC)*",,,Poster,http://arxiv.org/abs/2207.09176,,,, My View is the Best View: Procedure Learning from Egocentric Videos,"Siddhant Bansal (IIIT, Hyderabad)*; Chetan Arora (Indian Institute of Technology Delhi); C.V. Jawahar (IIIT-Hyderabad)",,,Poster,http://arxiv.org/abs/2207.10883,,,, Trace Controlled Text to Image Generation,Kun Yan (Beihang University)*; Lei Ji (Microsoft); Chenfei Wu (Microsoft); Jianmin Bao (microsoft.com); Ming Zhou (SINOVATION VENTURES); Nan Duan (Microsoft Research); Shuai Ma (Beihang University),,,Poster,,,,, Towards Comprehensive Representation Enhancement in Semantics-guided Self-supervised Monocular Depth Estimation,Jingyuan Ma (HikVision Research Institute)*; Xiangyu Lei (Hikvision Research Institute); Nan Liu (hikvison); Zhao Xian (Hikvision); Shiliang Pu (Hikvision Research Institute),,,Poster,,,,, @@ -519,10 +518,10 @@ Rethinking Robust Representation Learning Under Fine-grained Noisy Faces,"Bingqi Feature Representation Learning for Unsupervised Cross-domain Image Retrieval,Conghui Hu (National University of Singapore)*; Gim Hee Lee (National University of Singapore),,,Poster,http://arxiv.org/abs/2207.09721,https://github.com/conghuihu/UCDIR,,, Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation,sunghwan hong (Korea University); Seokju Cho (Korea University); Jisu Nam (korea university); Stephen Lin (Microsoft Research); Seungryong Kim (Korea University)*,,,Poster,http://arxiv.org/abs/2207.10866,,,, Spatial-Frequency Domain Information Integration for Pan-sharpening,man zhou (University of Science and Technology of China); Jie Huang (University of Science and Technology of China); Keyu Yan (University of Science and Technology of China); Hu Yu (University of Science and Technology of China); Xueyang Fu (University of Science and Technology of China); Aiping Liu (University of Science and Technology of China); Xian Wei (East China Normal University); Feng Zhao (University of Science and Technology of China)*,,,Poster,,,,, -TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement,"Keyang Zhou (University of Tübingen)*; Bharat Lal Bhatnagar (University of Tübingen, MPI informatik); Jan E. Lenssen (TU Dortmund); Gerard Pons-Moll (University of Tübingen)",,,Poster,http://arxiv.org/abs/2205.07982,,,, +TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement,"Keyang Zhou (University of Tübingen)*; Bharat Lal Bhatnagar (University of Tübingen, MPI informatik); Jan E. Lenssen (TU Dortmund); Gerard Pons-Moll (University of Tübingen)",,,Poster,http://arxiv.org/abs/2205.07982,,,, HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation,Lukas Hoyer (ETH Zurich)*; Dengxin Dai (ETH Zurich); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2204.13132,https://github.com/lhoyer/HRDA,,, Combating Label Distribution Shift for Active Domain Adaptation,Sehyun Hwang (POSTECH)*; Sohyun Lee (POSTECH); Sungyeon Kim (POSTECH); Jungseul Ok (POSTECH); Suha Kwak (POSTECH),,,Poster,http://arxiv.org/abs/2208.06604,,,, -GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation,Cristiano Saltori (University of Trento)*; Evgeny Krivosheev (University of Trento); Stéphane Lathuilière (Telecom-Paris); Nicu Sebe (University of Trento); Fabio Galasso (Sapienza University); Giuseppe Fiameni (NVIDIA); Elisa Ricci (University of Trento); Fabio Poiesi (Fondazione Bruno Kessler),,,Poster,http://arxiv.org/abs/2207.09763,https://github.com/saltoricristiano/gipso-sfouda,,, +GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation,Cristiano Saltori (University of Trento)*; Evgeny Krivosheev (University of Trento); Stéphane Lathuilière (Telecom-Paris); Nicu Sebe (University of Trento); Fabio Galasso (Sapienza University); Giuseppe Fiameni (NVIDIA); Elisa Ricci (University of Trento); Fabio Poiesi (Fondazione Bruno Kessler),,,Poster,http://arxiv.org/abs/2207.09763,https://github.com/saltoricristiano/gipso-sfouda,,, SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud,Xiangrui Zhao (Zhejiang University)*; Sheng Yang (Alibaba Group); Tianxin Huang (Zhejiang University); Jun Chen (Zhejiang University); Teng Ma (Alibaba Group); Mingyang Li (Alibaba A.I. Labs); Yong Liu (Zhejiang University),,,Poster,http://arxiv.org/abs/2208.01925,https://github.com/zxrzju/SuperLine3D.git,,, Efficient Meta-Tuning for Content-aware Neural Video Delivery,"Xiaoqi Li (Columbia university in the city of New york)*; Jiaming Liu (Peking University); Shizun Wang (Beijing University of Posts and Telecommunications); Cheng Lyu (Beijing University of Posts and Telecommunications); Ming Lu (Intel Labs China); Yurong Chen (Intel Labs China); Anbang Yao (Intel Labs China); Yandong Guo (OPPO Research Institute); Shanghang Zhang (University of California, Berkeley)",,,Poster,http://arxiv.org/abs/2207.09691,https://github.com/Neural-video-delivery/EMT-Pytorch-ECCV2022,,, PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation,Wentao Jiang (Beihang University)*; Sheng Jin (The University of Hong Kong); Wentao Liu (Sensetime); Chen Qian (SenseTime); Ping Luo (The University of Hong Kong); Si Liu (Beihang University),,,Poster,http://arxiv.org/abs/2208.07755,,,, @@ -531,11 +530,11 @@ Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality,Yue Son CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation,Cristiano Saltori (University of Trento)*; Fabio Galasso (Sapienza University); Giuseppe Fiameni (NVIDIA); Nicu Sebe (University of Trento); Elisa Ricci (University of Trento); Fabio Poiesi (Fondazione Bruno Kessler),,,Poster,http://arxiv.org/abs/2207.09778,https://github.com/saltoricristiano/cosmix-uda,,, Streaming Multiscale Deep Equilibrium Models,Can Ufuk Ertenli (Middle East Technical University)*; Emre Akbas (METU); Ramazan Gokberk Cinbis (METU),,,Poster,http://arxiv.org/abs/2204.13492,,,, AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture,Zhe Li (Tsinghua University)*; Zerong Zheng (Tsinghua University); Hongwen Zhang (Tsinghua University); Chaonan Ji (Tsinghua University); Yebin Liu (Tsinghua University),,,Poster,http://arxiv.org/abs/2207.02031,https://github.com/lizhe00/AvatarCap,,, -Hierarchical Average Precision Training for Pertinent Image Retrieval,"Elias Ramzi (Conservatoire Nation des Arts et Metiers)*; Nicolas Audebert (Cnam); Nicolas Thome (CNAM, Paris); Clément Rambour (Cnam); Xavier B Bitot (Coexya)",,,Poster,http://arxiv.org/abs/2207.04873,https://github.com/elias-ramzi/HAPPIER,,, +Hierarchical Average Precision Training for Pertinent Image Retrieval,"Elias Ramzi (Conservatoire Nation des Arts et Metiers)*; Nicolas Audebert (Cnam); Nicolas Thome (CNAM, Paris); Clément Rambour (Cnam); Xavier B Bitot (Coexya)",,,Poster,http://arxiv.org/abs/2207.04873,https://github.com/elias-ramzi/HAPPIER,,, "Fashionformer: A Simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition",Shilin Xu (Peking University); Xiangtai Li (Peking University)*; Jingbo Wang (The Chinese University of HongKong); Guangliang Cheng (Sensetime Group Limited); Yunhai Tong (Peking University); Dacheng Tao (JD.com),,,Poster,http://arxiv.org/abs/2204.04654,https://github.com/xushilin1/FashionFormer,,, Out-of-Distribution Detection with Semantic Mismatch under Masking,Yijun Yang (The Chinese University of Hong Kong)*; Ruiyuan Gao (The Chinese University of Hong Kong); Qiang Xu (The Chinese University of Hong Kong),,,Poster,http://arxiv.org/abs/2208.00446,,,, Target-absent Human Attention,Zhibo Yang (Stony Brook University)*; Sounak Mondal (Stony Brook University); Seoyoung Ahn (Stony Brook University); Gregory Zelinsky (Stony Brook University); Minh Hoai (Stony Brook University); Dimitris Samaras (Stony Brook University),,,Poster,http://arxiv.org/abs/2207.01166,,,, -Reference-based Image Super-Resolution with Deformable Attention Transformer,Jiezhang Cao (ETH Zürich)*; Jingyun Liang (ETH Zurich); Kai Zhang (ETH Zurich); Yawei Li (ETH Zurich); Yulun Zhang (ETH Zurich); Wenguan Wang (Eidgenössische Technische Hochschule Zürich); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.11938,,,, +Reference-based Image Super-Resolution with Deformable Attention Transformer,Jiezhang Cao (ETH Zürich)*; Jingyun Liang (ETH Zurich); Kai Zhang (ETH Zurich); Yawei Li (ETH Zurich); Yulun Zhang (ETH Zurich); Wenguan Wang (Eidgenössische Technische Hochschule Zürich); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.11938,,,, Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers,Junhyeong Cho (POSTECH)*; Kim Youwang (POSTECH); Tae-Hyun Oh (POSTECH),,,Poster,http://arxiv.org/abs/2207.13820,,,, Learning to Generate Realistic LiDAR Point Cloud,Vlas Zyrianov (University of Illinois Urbana Champaign); Xiyue Zhu (university of illinois); Shenlong Wang (UIUC)*,,,Poster,,,,, GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mapping,Pan Ji (OPPO US Research Center)*; Qingan Yan (OPPO US Research Center); Yuxin Ma (Wing LLC); Yi Xu (OPPO US Research Center),,,Poster,http://arxiv.org/abs/2205.01656,,,, @@ -593,7 +592,7 @@ CoupleFace: Relation Matters for Face Recognition Distillation,Jiaheng Liu (Beih Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition,Qinying Liu (University of Science and Technology of China); Zilei Wang (University of Science and Technology of China)*,,,Poster,http://arxiv.org/abs/2207.09767,,,, Adaptive Spatial-BCE Loss for Weakly Supervised Semantic Segmentation,Tong Wu (Beijing Institute of Technology); Guangyu Ryan Gao (Beijing Institute of Technology)*; junshi huang (Meituan); Xiaolin Wei (Meituan); Xiaoming Wei (Meituan); Chi Harold Liu (Beijing Institute of Technology),,,Poster,,,,, Multi-Person 3D Pose and Shape Estimation via Inverse Kinematics and Refinement,Junuk Cha (UNIST)*; Muhammad Saqlain (Ulsan National Institute of Science and Technology); GeonU Kim (UNIST); Mingyu Shin (ULSAN NATIONAL INSTITUTE OF SCIENCE AND TECHNOLOGY); Seungryul Baek (UNIST),,,Poster,,,,, -Explaining Deepfake Detection by Analysing Image Matching,Shichao Dong (Megvii); Jin Wang (Megvii); Haoqiang Fan (Megvii Inc（face++）); Jiajun Liang (Megvii); Renhe Ji (Megvii)*,,,Poster,http://arxiv.org/abs/2207.09679,,,, +Explaining Deepfake Detection by Analysing Image Matching,Shichao Dong (Megvii); Jin Wang (Megvii); Haoqiang Fan (Megvii Inc（face++）); Jiajun Liang (Megvii); Renhe Ji (Megvii)*,,,Poster,http://arxiv.org/abs/2207.09679,,,, L-CoDer: Language-based Colorization with Color-object Decoupling Transformer,Zheng Chang (Beijing University of Posts and Telecommunications); Shuchen Weng (Peking University)*; Yu Li (International Digital Economy Academy); Si Li (Beijing University of Posts and Telecommunications); Boxin Shi (Peking University),,,Poster,,,,, GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation,Shi Gong (Huazhong University of Science and Technology); Xiaoqing Ye (Baidu Inc.); Xiao Tan (Baidu Inc.); Jingdong Wang (Baidu); Errui Ding (Baidu Inc.); Yu Zhou (Huazhong University of Science and Technology)*; Xiang Bai (Huazhong University of Science and Technology),,,Poster,http://arxiv.org/abs/2204.07733,,,, Unsupervised Deep Multi-Shape Matching,Dongliang Cao (Technical University of Munich); Florian Bernard (University of Bonn)*,,,Poster,http://arxiv.org/abs/2207.09610,,,, @@ -602,7 +601,7 @@ EAutoDet: Efficient Architecture Search for Object Detection,"Xiaoxing Wang (Sha A Max-Flow based Approach for Neural Architecture Search,Chao Xue (beijing university of posts and telecommunications)*; Xiaoxing Wang (Shanghai Jiao Tong University); Junchi Yan (Shanghai Jiao Tong University); Chun-Guang Li (Beijing University of Posts & Telecommunications),,,Poster,,,,, Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding,Jiachang Hao (Beijing University of Posts and Telecommunications)*; Haifeng Sun (Beijing university of posts and telecommunications); Pengfei Ren (Beijing University of Posts and Telecommunications); Jingyu Wang (Beijing University of Posts and Telecommunications); Qi Qi (Beijing University of Posts and Telecommunications); Jianxin Liao (beijing university of posts and telecommunications),,,Poster,http://arxiv.org/abs/2207.14698,https://github.com/haojc/ShufflingVideosForTSG,,, tSF: Transformer-based Semantic Filter for Few-Shot Learning,Jinxiang Lai (Tencent)*; Siqian Yang (Tencent); Wenlong Liu (Tencent); Yi Zeng (Tencent); Zhongyi Huang (Tencent); Wenlong Wu (Tencent); Jun Liu (Tencent); Bin-Bin Gao (Tencent); Chengjie Wang (Tencent; Shanghai Jiao Tong University),,,Poster,,,,, -Dense Gaussian Processes for Few-Shot Segmentation,Joakim Johnander (Linköping University)*; Johan Edstedt (Linköping University); Fahad Shahbaz Khan (MBZUAI); Michael Felsberg (Linköping University); Martin Danelljan (ETH Zurich),,,Poster,http://arxiv.org/abs/2110.03674,,,, +Dense Gaussian Processes for Few-Shot Segmentation,Joakim Johnander (Linköping University)*; Johan Edstedt (Linköping University); Fahad Shahbaz Khan (MBZUAI); Michael Felsberg (Linköping University); Martin Danelljan (ETH Zurich),,,Poster,http://arxiv.org/abs/2110.03674,,,, Adversarial Feature Augmentation for Cross-domain Few-shot Classification,Yanxu Hu (Sun Yat-sen University); Andy J Ma (Sun Yat-sen University)*,,,Poster,http://arxiv.org/abs/2208.11021,https://github.com/youthhoo/AFA_For_Few_shot_learning,,, Real-Time Neural Character Rendering with Pose-Guided Multiplane Images,Hao Ouyang (HKUST)*; Bo Zhang (Microsoft Research Asia); Pan Zhang (Shanghai AI Laboratory); Hao Yang (Microsoft Research Asia); Dong Chen (Microsoft Research Asia); Jiaolong Yang (Microsoft Research); Qifeng Chen (HKUST); Fang Wen (Microsoft Research Asia ),,,Poster,http://arxiv.org/abs/2204.11820,,,, Constructing Balance from Imbalance for Long-tailed Image Recognition,Yue Xu (Shanghai Jiao Tong University); Yong-Lu Li (Shanghai Jiao Tong University); Jiefeng Li (Shanghai Jiao Tong University); Cewu Lu (Shanghai Jiao Tong University)*,,,Poster,http://arxiv.org/abs/2208.02567,https://github.com/silicx/DLSA,,, @@ -623,7 +622,7 @@ Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Autoregressive 3D Shape Generation via Canonical Mapping,"An-Chieh Cheng (National Tsing Hua University); Xueting Li (University of California, Merced); Sifei Liu (NVIDIA)*; Min Sun (NTHU); Ming-Hsuan Yang (University of California at Merced)",,,Poster,http://arxiv.org/abs/2204.01955,,,, Learning Continuous Implicit Representation for Near-Periodic Patterns,"Bowei Chen (CMU)*; Tiancheng Zhi (ByteDance); Martial Hebert (cmu); Srinivasa Narasimhan (Carnegie Mellon University, USA)",,,Poster,http://arxiv.org/abs/2208.12278,,,, Robust Landmark-based Stent Tracking in X-ray Fluoroscopy,Luojie Huang (Johns Hopkins Uniersity); Yikang Liu (United Imaging Intelligence America); Li Chen (University of Washington); Eric Z. Chen (United Imaging Intelligence America); Xiao Chen (United Imaging Intelligence America); Shanhui Sun (United Imaging Intelligence America)*,,,Poster,,,,, -Depth Field Networks for Generalizable Multi-view Scene Representation,Vitor Guizilini (Toyota Research Institute)*; Igor Vasiljevic (Toyota Research Institute); Jiading Fang (Toyota Technological Institute at Chicago); Rareș A Ambruș (Toyota Research Institute); Greg Shakhnarovich (Toyota Technological Institute at Chicago); Matthew Walter (Toyota Technological Institute at Chicago); Adrien Gaidon (Toyota Research Institute),,,Poster,http://arxiv.org/abs/2207.14287,,,, +Depth Field Networks for Generalizable Multi-view Scene Representation,Vitor Guizilini (Toyota Research Institute)*; Igor Vasiljevic (Toyota Research Institute); Jiading Fang (Toyota Technological Institute at Chicago); RareÈ™ A AmbruÈ™ (Toyota Research Institute); Greg Shakhnarovich (Toyota Technological Institute at Chicago); Matthew Walter (Toyota Technological Institute at Chicago); Adrien Gaidon (Toyota Research Institute),,,Poster,http://arxiv.org/abs/2207.14287,,,, Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation,"Simone Rossetti (Sapienza University); Damiano Zappia (Deepplants S.r.l.); Marta Sanzari (Sapienza University of Rome); Marco Schaerf (Sapienza University of Rome); fiora pirri (University of Rome, Sapienza)*",,,Poster,,,,, GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features,Van-Quang Nguyen (Tohoku University)*; Masanori Suganuma (Tohoku University / RIKEN AIP); Takayuki Okatani (Tohoku University/RIKEN AIP),,,Poster,http://arxiv.org/abs/2207.09666,,,, Learning Semantic Correspondence with Sparse Annotations,"Shuaiyi Huang (University of Maryland, College Park)*; Luyu Yang (University of Maryland, College Park); Bo He (University of Maryland); Songyang Zhang (Shanghai AI Laboratory); Xuming He (ShanghaiTech University); Abhinav Shrivastava (University of Maryland)",,,Poster,http://arxiv.org/abs/2208.06974,,,, @@ -636,7 +635,7 @@ Dense Siamese Network for Dense Unsupervised Learning,Wenwei Zhang (NTU)*; Jiang Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction,Hu Wang (the University of Adelaide)*; Jianpeng Zhang (Northwestern Polytechnical University); Yuanhong Chen (University of Adelaide); Congbo Ma (The University of Adelaide); Jodie C Avery (University of Adelaide); Mary L Hull (University of Adelaide); Gustavo Carneiro (University of Adelaide),,,Poster,http://arxiv.org/abs/2207.10851,,,, Enhanced Accuracy and Robustness via Multi-Teacher Adversarial Distillation,"Shiji Zhao (Beihang University); Jie Yu (Beihang University); Zhenlong Sun (Tencent Technology Co.Ltd); Bo Zhang (WeChat Search Application Department, Tencent); Xingxing Wei (Beihang University)*",,,Poster,,,,, End-to-end graph-constrained vectorized floorplan generation with panoptic refinement,Jiachen Liu (Pennsylvania State University)*; Yuan Xue (Johns Hopkins University); Jose P. Duarte (Penn State University); Krishnendra Shekhawat (BITS Pilani); Zihan Zhou (Manycore Tech Inc.); Sharon Xiaolei Huang (The Pennsylvania State University),,,Poster,http://arxiv.org/abs/2207.13268,,,, -Context Enhanced Stereo Transformer,weiyu Guo (University of Chinese Academy of Sciences)*; Zhaoshuo Li (Johns Hopkins University); Yongkui Yang (Shenzhen Institute of Advanced Technology，Chinese Academy of Sciences); Zheng Wang (Shenzhen Institutes of Advanced Technology); Russ Taylor (Johns Hopkins University); Mathias Unberath (Johns Hopkins University); Alan Yuille (Johns Hopkins University); Yingwei Li (Johns Hopkins University),,,Poster,,,,, +Context Enhanced Stereo Transformer,weiyu Guo (University of Chinese Academy of Sciences)*; Zhaoshuo Li (Johns Hopkins University); Yongkui Yang (Shenzhen Institute of Advanced Technology，Chinese Academy of Sciences); Zheng Wang (Shenzhen Institutes of Advanced Technology); Russ Taylor (Johns Hopkins University); Mathias Unberath (Johns Hopkins University); Alan Yuille (Johns Hopkins University); Yingwei Li (Johns Hopkins University),,,Poster,,,,, NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition,"Boyang Xia (Institute of Computing Technology, Chinese Academy of Science); Wenhao Wu (Baidu)*; Haoran Wang (Baidu); RUI SU (the University of Sydney); Dongliang He (Baidu); Haosen Yang (Harbin Institute of Technology); Xiaoran Fan (Institute of Computing Technology, Chinese Academy of Sciences); Wanli Ouyang (The University of Sydney)",,,Poster,http://arxiv.org/abs/2207.10388,,,, Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning,Yuxiao Chen (Rutgers University)*; Long Zhao (Google Research); Jianbo Yuan (Bytedance); Yu Tian (Rutgers); zhaoyang xia (Rutgers University); Shijie Geng (Rutgers University); Ligong Han (Rutgers University); Dimitris N. Metaxas (Rutgers),,,Poster,http://arxiv.org/abs/2207.09644,,,, Few-Shot Video Object Detection,Qi Fan (HKUST)*; Chi-Keung Tang (Hong Kong University of Science and Technology); Yu-Wing Tai (Kuaishou Technology / HKUST),,,Poster,http://arxiv.org/abs/2104.14805,https://github.com/fanq15/FewX,,, @@ -648,7 +647,7 @@ Few-shot Image Generation with Mixup-based Distance Learning,Chaerin Kong (Seoul Data-Free Neural Architecture Search via Recursive Label Calibration,"Zechun Liu (Carnegie Mellon University); Zhiqiang Shen (Carnegie Mellon University)*; Yun Long (Google); Eric Xing (MBZUAI, CMU, and Petuum Inc.); Kwang-Ting Cheng (Hong Kong University of Science and Technology); Chas H Leichner (Google)",,,Poster,http://arxiv.org/abs/2112.02086,,,, Distilling Object Detectors With Global Knowledge,Sanli Tang (Hikvision Research Institute); Zhongyu Zhang (Hikvision Research Institute); Zhanzhan Cheng (Zhejiang University & Hikvision Research Institute)*; Jing Lu (Hikvision Research Institute); Yunlu Xu (Hikvision Research Institute); Yi Niu (Hikvision Research Institute); Fan He (Shanghai Jiao Tong University),,,Poster,,,,, NEST: Neural Event Stack for Event-based Image Enhancement,Minggui Teng (Peking University)*; Chu Zhou (Peking University); Hanyue Lou (Peking University); Boxin Shi (Peking University),,,Poster,,,,, -Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation,"Jie Qin (School of Artificial Intelligence, University of Chinese Academy of Sciences; Institute of Automation，Chinese Academy of Sciences)*; Jie Wu (ByteDance Inc); Ming Li (Xiamen University); Xuefeng Xiao (ByteDance Inc); Min Zheng (ByteDance); Xingang Wang (Institute of Automation, CAS)",,,Poster,http://arxiv.org/abs/2208.10169,,,, +Multi-Granularity Distillation Scheme Towards Lightweight Semi-Supervised Semantic Segmentation,"Jie Qin (School of Artificial Intelligence, University of Chinese Academy of Sciences; Institute of Automation，Chinese Academy of Sciences)*; Jie Wu (ByteDance Inc); Ming Li (Xiamen University); Xuefeng Xiao (ByteDance Inc); Min Zheng (ByteDance); Xingang Wang (Institute of Automation, CAS)",,,Poster,http://arxiv.org/abs/2208.10169,,,, A Style-Based GAN Encoder for High Fidelity Reconstruction of Images and Videos,Xu YAO (Telecom ParisTech)*; Alasdair Newson (Telecom Paris); Yann Gousseau (Telecom Paris); PIERRE HELLIER (Interdigital (Technicolor)),,,Poster,,,,, Unifying Visual Perception by Dispersible Points Learning,Jianming Liang (Beihang University)*; Guanglu Song (Sensetime); Biao Leng (Beihang University); Yu Liu (SenseTime Group LTD),,,Poster,http://arxiv.org/abs/2208.08630,https://github.com/Sense-X/UniHead,,, Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes,"Haolin Liu (The Chinese University of Hong Kong, Shenzhen)*; Yujian Zheng (The Chinese University of Hong Kong, Shenzhen); Guanying CHEN (The Chinese University of Hong Kong, Shenzhen); Shuguang Cui (The Chinese University of Hong Kong, Shenzhen ); Xiaoguang Han (Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong (Shenzhen))",,,Poster,http://arxiv.org/abs/2207.08656,,,, @@ -656,18 +655,18 @@ Multimodal Transformer for Automatic 3D Annotation and Object Detection,Chang Li SP-Net: Slowly Progressing Dynamic Inference Networks,"Huanyu Wang (Zhejiang University)*; Wenhu Zhang (Zhejiang University); Shihao Su (Zhejiang University); Hui Wang (Zhejiang University); Zhenwei Miao (DAMO Academy, Alibaba Group); Xin Zhan (DAMO Academy, Alibaba Group); Xi Li (Zhejiang University)",,,Poster,,,,, No Token Left Behind: Explainability-Aided Image Classification and Generation,"Roni Paiss (Tel Aviv University, Google); Hila Chefer (Tel Aviv University)*; Lior Wolf (Tel Aviv University, Israel)",,,Poster,http://arxiv.org/abs/2204.04908,,,, Dynamically Transformed Instance Normalization Network for Generalizable Person Re-Identification,BingLiang Jiao (Northwestern Polytechnical University ); Lingqiao Liu (University of Adelaide); Liying Gao ( Northwestern Polytechnical University); Guosheng Lin (Nanyang Technological University); Lu Yang (Northwestern Polytechnical University); Shizhou Zhang (NorthWestern Polytechnical University); Peng Wang (Northwestern Polytechnical University)*; Yanning Zhang (Northwestern Polytechnical University),,,Poster,,,,, -Editable Indoor Lighting Estimation,Henrique Weber (Université Laval)*; Mathieu Garon (Depix); Jean-Francois Lalonde (Université Laval),,,Poster,,,,, +Editable Indoor Lighting Estimation,Henrique Weber (Université Laval)*; Mathieu Garon (Depix); Jean-Francois Lalonde (Université Laval),,,Poster,,,,, PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection,Gang Li (Nanjing University of Science and Technology)*; Xiang Li (Nanjing University of Science and Technology); Yujie Wang (Sensetime Research); Yichao Wu (Sensetime Group Limited); Ding Liang (Sensetime Group Limited); Shanshan Zhang (Max Planck Institute for Informatics),,,Poster,http://arxiv.org/abs/2203.16317,https://github.com/ligang-cs/PseCo,,, CompNVS: Novel View Synthesis with Scene Completion,Zuoyue Li (ETH Zurich)*; Tianxing Fan (Zhejiang University); Zhenqiang Li (The University of Tokyo); Zhaopeng Cui (Zhejiang University); Yoichi Sato (University of Tokyo); Marc Pollefeys (ETH Zurich / Microsoft); Martin R. Oswald (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.11467,,,, -Dynamic 3D Scene Analysis by Point Cloud Accumulation,Shengyu Huang (ETH Zürich)*; Zan Gojcic (NVIDIA); Jiahui Huang (Tsinghua University); Andreas Wieser (ETH Zürich); Konrad Schindler (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.12394,,,, +Dynamic 3D Scene Analysis by Point Cloud Accumulation,Shengyu Huang (ETH Zürich)*; Zan Gojcic (NVIDIA); Jiahui Huang (Tsinghua University); Andreas Wieser (ETH Zürich); Konrad Schindler (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.12394,,,, FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs,"Ziqiang Li (University of Science and Technology of China)*; Chaoyue Wang (JD.com); Heliang Zheng (JD Explore Academy, JD.com); Jing Zhang (The University of Sydney); Bin Li (University of Science and Technology of China)",,,Poster,http://arxiv.org/abs/2207.08630,https://github.com/iceli1007/FakeCLR,,, Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction,Chia-Chi Chuang (Tsinghua University); Donglin Yang (Tsinghua University); Chuan Wen (Tsinghua University)*; Yang Gao (Tsinghua University),,,Poster,http://arxiv.org/abs/2207.09705,,,, -REALY: Rethinking the Evaluation of 3D Face Reconstruction,Zenghao Chai (Tsinghua University); Haoxian Zhang (Tencent); Jing Ren (ETH Zurich); Di Kang (Tencent); Zhengzhuo Xu (Tsinghua University); Xuefei Zhe (Tencent AI lab); Chun Yuan (Graduate school at ShenZhen，Tsinghua university); Linchao Bao (Tencent AI Lab)*,,,Poster,http://arxiv.org/abs/2203.09729,,,, +REALY: Rethinking the Evaluation of 3D Face Reconstruction,Zenghao Chai (Tsinghua University); Haoxian Zhang (Tencent); Jing Ren (ETH Zurich); Di Kang (Tencent); Zhengzhuo Xu (Tsinghua University); Xuefei Zhe (Tencent AI lab); Chun Yuan (Graduate school at ShenZhen，Tsinghua university); Linchao Bao (Tencent AI Lab)*,,,Poster,http://arxiv.org/abs/2203.09729,,,, TransMatting: Enhancing Transparent Objects Matting with Transformers,"huanqia cai (University of Chinese Academy of Sciences)*; Fanglei Xue (University of Chinese Academy of Sciences); Lele Xu (Key Laboratory of Space Utilization, Technology and Engineering Center for space Utilization, Chinese Academy of Sciences.); lili guo (Key Laboratory of Space Utilization, Technology and Engineering Center for space Utilization, Chinese Academy of Sciences. )",,,Poster,http://arxiv.org/abs/2208.03007,,,, -Diverse Image Inpainting with Normalizing Flow,"Cairong Wang (Graduate school at Shenzhen, Tsinghua University)*; Yiming M Zhu (Graduate school at ShenZhen，Tsinghua university); Chun Yuan (Graduate school at ShenZhen，Tsinghua university)",,,Poster,,,,, +Diverse Image Inpainting with Normalizing Flow,"Cairong Wang (Graduate school at Shenzhen, Tsinghua University)*; Yiming M Zhu (Graduate school at ShenZhen，Tsinghua university); Chun Yuan (Graduate school at ShenZhen，Tsinghua university)",,,Poster,,,,, Video Activity Localisation with Uncertainties in Temporal Boundary,Jiabo Huang (Queen Mary University of London)*; Hailin Jin (Adobe Research); Shaogang Gong (Queen Mary University of London); Yang Liu (Peking University),,,Poster,http://arxiv.org/abs/2206.12923,,,, SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling,Chenjian Gao (Beihang University); Qian Yu (Beihang University)*; Lu Sheng (Beihang University); Yi-Zhe Song (University of Surrey); Dong Xu (The University of Hong Kong),,,Poster,http://arxiv.org/abs/2208.06880,,,, -Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection,Ziteng Cui (The University of Tokyo); Yingying Zhu (University of Texas Arlington); Lin Gu (RIKEN，AIP / The University of Tokyo)*; Guo-Jun Qi (Futurewei Technologies); Xiaoxiao Li (The University of British Columbia); Renrui Zhang (Shanghai AI Lab); Zenghui Zhang (Shanghai Jiao Tong university); Tatsuya Harada (The University of Tokyo / RIKEN),,,Poster,http://arxiv.org/abs/2208.03062,https://github.com/cuiziteng/ECCV_AERIS,,, +Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection,Ziteng Cui (The University of Tokyo); Yingying Zhu (University of Texas Arlington); Lin Gu (RIKEN，AIP / The University of Tokyo)*; Guo-Jun Qi (Futurewei Technologies); Xiaoxiao Li (The University of British Columbia); Renrui Zhang (Shanghai AI Lab); Zenghui Zhang (Shanghai Jiao Tong university); Tatsuya Harada (The University of Tokyo / RIKEN),,,Poster,http://arxiv.org/abs/2208.03062,https://github.com/cuiziteng/ECCV_AERIS,,, CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation,Feng Wang (Tsinghua University)*; Huiyu Wang (JHU); Chen Wei (Johns Hopkins University); Alan Yuille (Johns Hopkins University); Wei Shen (Shanghai Jiao Tong University),,,Poster,http://arxiv.org/abs/2203.11709,,,, Learning from Multiple Annotator Noisy Labels via Sample-wise Label Fusion,Zhengqi Gao (MIT)*; Fan-Keng Sun (MIT); Mingran Yang (MIT); Sucheng Ren (South China University of Technology); Zikai Xiong (Massachusetts Institute of Technology); Marc Engeler (Takeda); Antonio Burazer (Takeda); Linda Wildling (Takeda Pharmaceuticals International AG); Luca Daniel (Massachusetts Institute of Technology); Duane Boning (MIT),,,Poster,http://arxiv.org/abs/2207.11327,https://github.com/zhengqigao/Learning-from-Multiple-Annotator-Noisy-Labels,,, Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features,Wufei Ma (Purdue University)*; Angtian Wang (Johns Hopkins University); Alan Yuille (Johns Hopkins University); Adam Kortylewski (Max Planck Institute for Informatics),,,Poster,,,,, @@ -704,7 +703,7 @@ Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation,Z MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation,Tarun Kalluri (UC San Diego)*; Astuti Sharma (UCSD); Manmohan Chandraker (UC San Diego),,,Poster,http://arxiv.org/abs/2207.12389,,,, GCISG: Guided Causal Invariant Learning for Improved Syn-to-real Generalization,Gilhyun Nam (Agency for Defense Development)*; Gyeongjae Choi (Agency for Defense Development); Kyungmin Lee (Agency for Defense Development),,,Poster,http://arxiv.org/abs/2208.10024,,,, Temporal Saliency Query Network for Efficient Video Recognition,"Boyang Xia (Institute of Computing Technology, Chinese Academy of Science); Zhihao Wang (Institute of Computing Technology, Chinese Academy of Sciences); Wenhao Wu (Baidu)*; Haoran Wang (Baidu); Jungong Han (Aberystwyth University)",,,Poster,http://arxiv.org/abs/2207.10379,,,, -Towards Interpretable Video Super-Resolution via Alternating Optimization,Jiezhang Cao (ETH Zürich)*; Jingyun Liang (ETH Zurich); Kai Zhang (ETH Zurich); Wenguan Wang (Eidgenössische Technische Hochschule Zürich); Qin Wang (ETH Zurich); Yulun Zhang (ETH Zurich); Hao Tang (ETH Zurich); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.10765,,,, +Towards Interpretable Video Super-Resolution via Alternating Optimization,Jiezhang Cao (ETH Zürich)*; Jingyun Liang (ETH Zurich); Kai Zhang (ETH Zurich); Wenguan Wang (Eidgenössische Technische Hochschule Zürich); Qin Wang (ETH Zurich); Yulun Zhang (ETH Zurich); Hao Tang (ETH Zurich); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.10765,,,, R-DFCIL: Relation-Guided Representation Learning for Data-Free Class Incremental Learning,Qiankun Gao (Peking University Shenzhen Graduate School)*; Chen Zhao (KAUST); Bernard Ghanem (KAUST); Jian Zhang (Peking University Shenzhen Graduate School),,,Poster,,,,, Spike Transformer: Monocular Depth Estimation for Spiking Camera,Jiyuan Zhang (Peking University)*; Lulu Tang (Tsingua University); Zhaofei Yu (Peking University); Jiwen Lu (Tsinghua University); Tiejun Huang (Peking University),,,Poster,,,,, Towards Robust Face Recognition with Comprehensive Search,Manyuan Zhang (Sensetime)*; Guanglu Song (Sensetime); Yu Liu (SenseTime Group LTD); Hongsheng Li (The Chinese University of Hong Kong),,,Poster,http://arxiv.org/abs/2208.13600,,,, @@ -713,7 +712,7 @@ Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction, RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection,Chang Xu (Wuhan University); Jinwang Wang (Huawei Technoloty); Wen Yang (Wuhan University)*; Huai Yu (Wuhan University); Lei Yu (Wuhan University); Gui-Song Xia (Wuhan University),,,Poster,http://arxiv.org/abs/2208.08738,https://github.com/Chasel-Tsui/mmdet-rfla,,, Semi-supervised Single-view 3D Reconstruction via Prototype Shape Priors,"Zhen Xing (Fudan University)*; Hengduo Li (University of Maryland, College Park ); Zuxuan Wu (UMD); Yu-Gang Jiang (Fudan University)",,,Poster,,,,, Sequential Multi-View Fusion Network for Fast LiDAR Point Motion Estimation,"Gang Zhang (Damo Academy, Alibaba Group)*; Xiaoyan Li (Beijing University of Technology); Zhenhua Wang (DAMO Academy, Alibaba Group)",,,Poster,,,,, -A Large-scale Multiple-objective Method for Black-box Attack against Object Detection,"Siyuan Liang (Chinese Academy of Sciences); Longkang Li (Mohamed bin Zayed University of Artificial Intelligence); Yanbo Fan (Tencent AI Lab); Xiaojun Jia (Institute of Information Engineering，Chinese Academy of Sciences); Jingzhi Li (Institute of information engineering, CAS); Baoyuan Wu (The Chinese University of Hong Kong, Shenzhen)*; Xiaochun Cao (Sun Yat-sen University)",,,Poster,,,,, +A Large-scale Multiple-objective Method for Black-box Attack against Object Detection,"Siyuan Liang (Chinese Academy of Sciences); Longkang Li (Mohamed bin Zayed University of Artificial Intelligence); Yanbo Fan (Tencent AI Lab); Xiaojun Jia (Institute of Information Engineering，Chinese Academy of Sciences); Jingzhi Li (Institute of information engineering, CAS); Baoyuan Wu (The Chinese University of Hong Kong, Shenzhen)*; Xiaochun Cao (Sun Yat-sen University)",,,Poster,,,,, GradAuto: Energy-oriented Attack on Dynamic Neural Networks,Jianhong Pan (Singapore University of Technology and Design)*; Qichen Zheng (Singapore University of Technology and Design); Zhipeng Fan (NYU TANDON SCHOOL OF ENGINEERING); Hossein Rahmani (Lancaster University); Qiuhong Ke (Monash University); Jun Liu (Singapore University of Technology and Design),,,Poster,,,,, Semantic-guided Multi-Mask Image Harmonization,Xuqian Ren (Watrix Technology); Yifan Liu (University of Adelaide)*,,,Poster,http://arxiv.org/abs/2207.11722,https://github.com/XuqianRen/Semantic-guided-Multi-mask-Image-Harmonization.git,,, Manifold Adversarial Learning for Cross-domain 3D Shape Representation,Hao Huang (New York University); Cheng Chen (New York University); Yi Fang (New York University)*,,,Poster,,,,, @@ -730,7 +729,7 @@ Pose2Room: Understanding 3D Scenes from Human Activities,"Yinyu Nie (Technical U "Capturing, Reconstructing, and Simulating: the UrbanScene3D Dataset",Liqiang Lin (Shenzhen University); Yilin Liu (Shenzhen University); Yue Hu (Shenzhen University); Xingguang Yan (Shenzhen University); Ke Xie (Shenzhen University); Hui Huang (Shenzhen University)*,,,Poster,http://arxiv.org/abs/2107.04286,,,, A Spectral View of Randomized Smoothing under Common Corruptions: Benchmarking and Improving Certified Robustness,Jiachen Sun (University of Michigan)*; Akshay Mehra (Tulane University); Bhavya Kailkhura (Lawrence Livermore National Laboratory); Pin-Yu Chen (IBM Research); Dan Hendrycks (UC Berkeley); Jihun Hamm (Tulane University); Zhuoqing Morley Mao (University of Michigan),,,Poster,,,,, CLIP-Actor: Text-Driven Recommendation and Stylization for Animating Human Meshes,Kim Youwang (POSTECH)*; Ji-Yeon Kim (POSTECH); Tae-Hyun Oh (POSTECH),,,Poster,,,,, -Interpretable Image Classification with Differentiable Prototypes Assignment,Dawid Damian Rymarczyk (Jagiellonian University)*; Łukasz Struski (Jagiellonian University); Michał Górszczak (Jagiellonian University); Koryna Lewandowska (Jagiellonian University); Jacek Tabor (Jagiellonian University); Bartosz Zieliński (Jagiellonian University),,,Poster,http://arxiv.org/abs/2112.02902,,,, +Interpretable Image Classification with Differentiable Prototypes Assignment,Dawid Damian Rymarczyk (Jagiellonian University)*; Å�ukasz Struski (Jagiellonian University); MichaÅ‚ Górszczak (Jagiellonian University); Koryna Lewandowska (Jagiellonian University); Jacek Tabor (Jagiellonian University); Bartosz ZieliÅ„ski (Jagiellonian University),,,Poster,http://arxiv.org/abs/2112.02902,,,, Efficient One-stage Video Object Detection by Exploiting Temporal Consistency,Guanxiong Sun (Queen's University Belfast); Yang Hua (Queen's University Belfast)*; Guosheng Hu (Oosto); Neil Robertson (Queen's University Belfast),,,Poster,,,,, ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images,Jiawei Yang (UCLA)*; Hanbo Chen (Tencent AI Lab); Yuan Liang (UCLA); Junzhou Huang (University of Texas at Arlington); Lei He (UCLA); Jianhua Yao (National Institutes of Health),,,Poster,http://arxiv.org/abs/2207.06733,,,, Leveraging Action Affinity and Continuity for Semi-supervised Temporal Action Segmentation,Guodong Ding (National University of Singapore)*; Angela Yao (National University of Singapore),,,Poster,http://arxiv.org/abs/2207.08653,,,, @@ -751,20 +750,20 @@ Improving Adversarial Robustness of 3D Point Cloud Classification Models,Guanlin ASSISTER: Assistive Navigation via Conditional Instruction Generation,Zanming Huang (Boston University); Zhongkai Shangguan (Boston University); Jimuyang Zhang (Boston University); Gilad Bar (Rutgers University - Camden); Matthew Boyd (Boston University); Eshed Ohn-Bar (Boston University)*,,,Poster,,,,, Deep Hash Distillation for Image Retrieval,Young Kyun Jang (Seoul National University)*; Geonmo Gu (NAVER corp); Byungsoo Ko (NAVER/LINE Corp.); Isaac Kang (Seoul National University); Nam Ik Cho (Seoul National University),,,Poster,http://arxiv.org/abs/2112.08816,,,, Learning Spatial-Preserved Skeleton Representations for Few-Shot Action Recognition,Ning Ma (Zhejiang University)*; Hongyi Zhang (Zhejiang University); Xuhui Li (Zhejiang University); Sheng Zhou (Zhejiang University); Zhen Zhang (National University of Singapore); Jun Wen (Harvard University); Haifeng Li (Zhejiang University); Jingjun Gu (Zhejiang University); Jiajun Bu (Zhejiang University),,,Poster,,,,, -Digging into Radiance Grid for Real-Time View Synthesis with Detail Preservation,"Jian Zhang (Alibaba Group); Jinchi Huang (Alibaba Group); Bowen Cai (Alibaba Group); Huan Fu (Alibaba Group)*; Mingming Gong (University of Melbourne); Chaohui Wang (Laboratoire d'Informatique Gaspard Monge, Université Paris-Est); Jiaming Wang (Alibaba Group); Hongchen Luo (Alibaba Group); Rongfei Jia (Alibaba Group); Binqiang Zhao (Alibaba); Xing Tang (Alibaba Group)",,,Poster,,,,, +Digging into Radiance Grid for Real-Time View Synthesis with Detail Preservation,"Jian Zhang (Alibaba Group); Jinchi Huang (Alibaba Group); Bowen Cai (Alibaba Group); Huan Fu (Alibaba Group)*; Mingming Gong (University of Melbourne); Chaohui Wang (Laboratoire d'Informatique Gaspard Monge, Université Paris-Est); Jiaming Wang (Alibaba Group); Hongchen Luo (Alibaba Group); Rongfei Jia (Alibaba Group); Binqiang Zhao (Alibaba); Xing Tang (Alibaba Group)",,,Poster,,,,, S^2Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning,Tze Ho Elden Tse (University of Birmingham)*; Zhongqun Zhang (University of Birmingham); Kwang In Kim (UNIST); Ales Leonardis (University of Birmingham); Feng Zheng (SUSTech); Hyung Jin Chang (University of Birmingham),,,Poster,,,,, TD-Road: Top-Down Road Network Extraction with Holistic Graph Construction,Yang He (Amazon)*; Ravi Garg (Amazon com services inc); Amber Roy Chowdhury (Amazon),,,Poster,,,,, StyleGAN-Human: A Data-Centric Odyssey of Human Generation,Jianglin Fu (SenseTime)*; Shikai Li (SenseTime Research); Yuming Jiang (Nanyang Technological University); Kwan-Yee Lin (SenseTime Research); Chen Qian (SenseTime); Chen Change Loy (Nanyang Technological University); Wayne Wu (SenseTime Research); Ziwei Liu (Nanyang Technological University),,,Poster,,,,, -Hourglass Attention Network for Image Inpainting,"Ye Deng (Xi’an Jiaotong University)*; Siqi Hui (Xi'an Jiaotong University); Rongye Meng (IAIR, Xi'an Jiaotong University); Sanping Zhou (Xi'an Jiaotong University); Jinjun Wang (Xi'an Jiaotong University)",,,Poster,,,,, +Hourglass Attention Network for Image Inpainting,"Ye Deng (Xi’an Jiaotong University)*; Siqi Hui (Xi'an Jiaotong University); Rongye Meng (IAIR, Xi'an Jiaotong University); Sanping Zhou (Xi'an Jiaotong University); Jinjun Wang (Xi'an Jiaotong University)",,,Poster,,,,, MaxViT: Multi-Axis Vision Transformer,Zhengzhong Tu (University of Texas at Austin)*; Hossein Talebi (Google); Han Zhang (Google); Feng Yang (Google Research); Peyman Milanfar (Google); Alan Bovik (University of Texas at Austin); Yinxiao Li (Google),,,Poster,http://arxiv.org/abs/2204.01697,https://github.com/google-research/maxvit,,, Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images,Yuan Liu (The University of Hong Kong)*; Yilin Wen (The University of Hong Kong); Sida Peng (Zhejiang University); Cheng Lin (Tencent); Xiaoxiao Long (The University of Hong Kong); Taku Komura (The University of Hong Kong); Wenping Wang (The University of Hong Kong),,,Poster,,,,, ColorFormer: Image Colorization via Color Memory assisted Hybrid-attention Transformer,Xiaozhong Ji (Tencent)*; Boyuan Jiang (Tencent Youtu Lab); Donghao Luo (Tencent); Guangpin Tao (Nanjing University); Wenqing Chu (Tencent); Zhifeng Xie (Shanghai University); Chengjie Wang (Tencent; Shanghai Jiao Tong University); Ying Tai (Tencent YouTu),,,Poster,,,,, -"Spotting Temporally Precise, Fine-Grained Events in Video",James Hong (Stanford University)*; Haotian Zhang (Stanford University); Michaël Gharbi (Adobe Research); Matthew Fisher (Adobe Research); Kayvon Fatahalian (Stanford),,,Poster,http://arxiv.org/abs/2207.10213,,,, +"Spotting Temporally Precise, Fine-Grained Events in Video",James Hong (Stanford University)*; Haotian Zhang (Stanford University); Michaël Gharbi (Adobe Research); Matthew Fisher (Adobe Research); Kayvon Fatahalian (Stanford),,,Poster,http://arxiv.org/abs/2207.10213,,,, SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness,Jindong Gu (University of Munich)*; Hengshuang Zhao (University of Oxford); Volker Tresp (Siemens AG and Ludwig Maximilian University of Munich ); Philip Torr (University of Oxford),,,Poster,http://arxiv.org/abs/2207.12391,,,, Adversarial Erasing Framework via Triplet with Gated Pyramid Pooling Layer for Weakly Supervised Semantic Segmentation,Sung-Hoon Yoon (KAIST)*; Hyeokjun Kweon (KAIST); Jegyeong Cho (KAIST); Shinjeong Kim (KAIST); Kuk-Jin Yoon (KAIST),,,Poster,,,,, Semi-Supervised Vision Transformers,Zejia Weng (Fudan University)*; Xitong Yang (University of Maryland); Ang Li (Google DeepMind); Zuxuan Wu (UMD); Yu-Gang Jiang (Fudan University),,,Poster,http://arxiv.org/abs/2111.11067,https://github.com/wengzejia1/Semiformer,,, Learning an Isometric Surface Parameterization for Texture Unwrapping,Sagnik Das (Stony Brook University)*; Ke Ma (Stony Brook University); Zhixin Shu (Adobe Research); Dimitris Samaras (Stony Brook University),,,Poster,,,,, -Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification,BOQIANG XU (University of Chinese Academy of Sciences；Institute of Automation，Chinese Academy of Sciences)*; Jian Liang (CASIA); He Lingxiao (nlpr，cripac); Zhenan Sun (Chinese of Academy of Sciences),,,Poster,http://arxiv.org/abs/2112.08684,https://github.com/xbq1994/META,,, +Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re-identification,BOQIANG XU (University of Chinese Academy of Sciencesï¼›Institute of Automation，Chinese Academy of Sciences)*; Jian Liang (CASIA); He Lingxiao (nlpr，cripac); Zhenan Sun (Chinese of Academy of Sciences),,,Poster,http://arxiv.org/abs/2112.08684,https://github.com/xbq1994/META,,, CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Images,Axel Levy (Stanford University); Frederic Poitevin (SLAC National Accelerator Laboratory); Julien N. P. Martel (Stanford University); Youssef Nashed (SLAC National Accelerator Laboratory); Ariana Peck (SLAC National Accelerator Laboratory); Nina Miolane (UCSB); Daniel Ratner (Stanford University ); Mike Dunne (SLAC National Accelerator Laboratory); Gordon Wetzstein (Stanford University)*,,,Poster,http://arxiv.org/abs/2203.08138,,,, EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs,Guohao Ying (University of Southern California); Xin He (Hong Kong Baptist University); Bin Gao (National University of Singapore); Bo Han (HKBU / RIKEN); Xiaowen Chu (Hong Kong University of Science and Technology)*,,,Poster,http://arxiv.org/abs/2111.15097,https://github.com/marsggbo/EAGAN,,, ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer,Rui Yang (Tsinghua University)*; Hailong Ma (ByteDance Inc); Jie Wu (ByteDance Inc); Yansong Tang (Tsinghua University); Xuefeng Xiao (ByteDance Inc); Min Zheng (ByteDance); Xiu Li (Tsinghua University),,,Poster,http://arxiv.org/abs/2203.10790,,,, @@ -797,7 +796,7 @@ Multimodal Conditional Image Synthesis with Product-of-Experts GANs,Xun Huang (N Balancing between Forgetting and Acquisition in Incremental Subpopulation Learning,Mingfu Liang (Northwestern University)*; JIAHUAN ZHOU (Peking University); Wei Wei (Northwestern University); Ying Wu (Northwestern University),,,Poster,,,,, TensoRF: Tensorial Radiance Fields,Anpei Chen (ShanghaiTech University)*; Zexiang Xu (Adobe Research); Andreas Geiger (University of Tuebingen); Jingyi Yu (Shanghai Tech University); Hao Su (UCSD),,,Poster,http://arxiv.org/abs/2203.09517,,,, PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration,Mingzhi Yuan (Fudan University)*; Zhihao Li (Fudan); Qiuye Jin (Fudan University); Xinrong Chen (Fudan University); Manning Wang (Fudan University),,,Poster,,,,, -Slim Scissors: Segmenting Thin Object from Synthetic Background,Kunyang Han (Beijing Jiaotong University)*; Jun Hao Liew (ByteDance); Jiashi Feng (ByteDance); Huawei Tian (People’s Public Security University of China); Yao Zhao (Beijing Jiaotong University); Yunchao Wei (UTS),,,Poster,,,,, +Slim Scissors: Segmenting Thin Object from Synthetic Background,Kunyang Han (Beijing Jiaotong University)*; Jun Hao Liew (ByteDance); Jiashi Feng (ByteDance); Huawei Tian (People’s Public Security University of China); Yao Zhao (Beijing Jiaotong University); Yunchao Wei (UTS),,,Poster,,,,, CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition,Shreyank N Gowda (University of Edinburgh)*; Laura Sevilla-Lara (Facebook); Frank Keller (University of Edinburgh); Marcus Rohrbach (Facebook AI Research),,,Poster,http://arxiv.org/abs/2101.07042,,,, Discovering Human-Object Interaction Concepts via Self-Compositional Learning,Zhi Hou (The University of Sydney)*; Baosheng Yu (The University of Sydney); Dacheng Tao (The University of Sydney),,,Poster,http://arxiv.org/abs/2203.14272,https://github.com/zhihou7/HOI-CL,,, Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance,"Chen Tang (Tsinghua University)*; Kai Ouyang (Tsinghua University); Zhi Wang (Tsinghua University); Yifei Zhu (Shanghai Jiao Tong University); Wen Ji (Institute of Computing Technology, Chinese Academy of Sciences); Yaowei Wang (PengCheng Laboratory); Wenwu Zhu (Tsinghua University)",,,Poster,http://arxiv.org/abs/2203.08368,,,, @@ -808,26 +807,26 @@ Convolutional Embedding Makes Hierarchical Vision Transformer Stronger,Cong Wang Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration,"Haotian Bai (The Chinese University of Hongkong, shenzhen); Ruimao Zhang (The Chinese University of Hong Kong, Shenzhen)*; Jiong WANG (The Chinese University of Hong Kong, Shenzhen); Xiang Wan (Shenzhen Research Institute of Big Data, the Chinese University of Hong Kong (Shenzhen))",,,Poster,http://arxiv.org/abs/2207.10447,https://github.com/164140757/SCM,,, Few-shot Class-incremental Learning for 3D Point Cloud Objects,"Townim Faisal Chowdhury (North South University); Ali Cheraghian (Australian National University (ANU)); Sameera Chandimal Ramasinghe (Australian National University); Sahar Ahmadi (University of Technology Sydney); Morteza Saberi (University of Technology, Sydney); Shafin Rahman (North South University)*",,,Poster,http://arxiv.org/abs/2205.15225,,,, Learning Graph Neural Networks for Image Style Transfer,Yongcheng Jing (The University of Sydney); Yining Mao (Zhejiang University); Yiding Yang (Wormpex AI Research); Yibing Zhan (JD Explore Academy); Mingli Song (Zhejiang University); Xinchao Wang (National University of Singapore)*; Dacheng Tao (JD.com),,,Poster,http://arxiv.org/abs/2207.11681,,,, -"JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes",Haimei Zhao (The University of Sydney)*; Jing Zhang (The University of Sydney); Sen Zhang (The University of Sydney); Dacheng Tao (JD.com),,,Poster,http://arxiv.org/abs/2207.07895,https://github.com/sunnyHelen/JPerceiver}{https://github.com/sunnyHelen/JPerceiver,,, +"JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes",Haimei Zhao (The University of Sydney)*; Jing Zhang (The University of Sydney); Sen Zhang (The University of Sydney); Dacheng Tao (JD.com),,,Poster,http://arxiv.org/abs/2207.07895,https://github.com/sunnyHelen/JPerceiver,,, Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions,"Zhenyi Wang (University at Buffalo)*; Li Shen (JD Explore Academy); Le Fang (University at Buffalo); Qiuling Suo (State University of New York at Buffalo); Donglin Zhan (Columbia University); Tiehang Duan (Facebook); Mingchen Gao (University at Buffalo, SUNY)",,,Poster,,,,, -Semi-supervised 3D Object Detection with Proficient Teachers,Junbo Yin (Beijing Institute of Technology); Jin Fang (Baidu ); Dingfu Zhou (Baidu); Wenguan Wang (Eidgenössische Technische Hochschule Zürich); Liangjun Zhang (baidu); Cheng-Zhong Xu (University of Macau); Jianbing Shen (Inception Institute of Artificial Intelligence)*,,,Poster,http://arxiv.org/abs/2207.12655,,,, -NeFSAC: Neurally Filtered Minimal Samples,Luca Cavalli (ETH Zurich)*; Marc Pollefeys (ETH Zurich / Microsoft); Daniel Barath (ETH Zürich),,,Poster,http://arxiv.org/abs/2207.07872,https://github.com/cavalli1234/NeFSAC,,, +Semi-supervised 3D Object Detection with Proficient Teachers,Junbo Yin (Beijing Institute of Technology); Jin Fang (Baidu ); Dingfu Zhou (Baidu); Wenguan Wang (Eidgenössische Technische Hochschule Zürich); Liangjun Zhang (baidu); Cheng-Zhong Xu (University of Macau); Jianbing Shen (Inception Institute of Artificial Intelligence)*,,,Poster,http://arxiv.org/abs/2207.12655,,,, +NeFSAC: Neurally Filtered Minimal Samples,Luca Cavalli (ETH Zurich)*; Marc Pollefeys (ETH Zurich / Microsoft); Daniel Barath (ETH Zürich),,,Poster,http://arxiv.org/abs/2207.07872,https://github.com/cavalli1234/NeFSAC,,, Domain Generalization by Mutual-Information Regularization with Pre-trained Models,"Junbum Cha (Kakaobrain)*; Kyungjae Lee (Chung-Ang University); Sungrae Park (Upstage AI Research, Upstage AI); Sanghyuk Chun (NAVER AI Lab)",,,Poster,http://arxiv.org/abs/2203.10789,https://github.com/kakaobrain/miro,,, AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection,"Yipeng Gao (Sun Yat-sen University, China); Lingxiao YANG (Sun-Yat Sen University); Yunmu Huang (Huawei Technologies Co., Ltd.); Song Xie (Huawei Technologies Co., Ltd.); Shiyong Li ( AI Application Research Center, Huawei Technologies Co., Ltd); WEI-SHI ZHENG (Sun Yat-sen University, China)*",,,Poster,,,,, Primitive-based Shape Abstraction via Nonparametric Bayesian Inference,Yuwei Wu (National University of Singapore)*; Weixiao Liu (National University of Singapore); Sipu Ruan (National University of Singapore); Gregory S Chirikjian (National University of Singapore),,,Poster,http://arxiv.org/abs/2203.14714,,,, Active label correction using robust parameter update and entropy propagation,Kwang In Kim (UNIST)*,,,Poster,,,,, E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs,"Yanyan Li (tum)*; Federico Tombari (Google, TU Munich)",,,Poster,,,,, -Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation,Nadine Behrmann (Bosch Center for Artificial Intelligence)*; S. Alireza Golestaneh (Google); Zico Kolter (Carnegie Mellon University); Jürgen Gall (University of Bonn); Mehdi Noroozi (Bosch Gmb),,,Poster,,,,, +Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation,Nadine Behrmann (Bosch Center for Artificial Intelligence)*; S. Alireza Golestaneh (Google); Zico Kolter (Carnegie Mellon University); Jürgen Gall (University of Bonn); Mehdi Noroozi (Bosch Gmb),,,Poster,,,,, Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identification,Xulin Li (University of Science and Technology of China); Yan Lu (University of Sydney); Bin Liu (University of Science and Technology of China)*; Yating Liu (USTC); Guojun Yin (University of Science and Technology of China); Qi Chu (University of Science and Technology of China); Jinyang Huang (University Of Science And Technology Of China); Feng Zhu (University of Science and Technology of China); Rui Zhao (SenseTime Group Limited); Nenghai Yu (University of Science and Technology of China),,,Poster,http://arxiv.org/abs/2208.00967,,,, A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision,Lanxiao Li (Karlsruher Institut fuer Technologie)*; Michael Heizmann (Karlsruher Institut fuer Technologie),,,Poster,http://arxiv.org/abs/2207.04997,,,, -VecGAN: Image-to-Image Translation with Interpretable Latent Directions,Yusuf Dalva (Bilkent University); Said F Altındiş (Bilkent University); Aysegul Dundar (Bilkent University)*,,,Poster,http://arxiv.org/abs/2207.03411,,,, +VecGAN: Image-to-Image Translation with Interpretable Latent Directions,Yusuf Dalva (Bilkent University); Said F AltındiÅŸ (Bilkent University); Aysegul Dundar (Bilkent University)*,,,Poster,http://arxiv.org/abs/2207.03411,,,, SNeS: Learning Probably Symmetric Neural Surfaces from Incomplete Data,Eldar Insafutdinov (University of Oxford); Dylan Campbell (University of Oxford)*; Joao F Henriques (University of Oxford); Andrea Vedaldi (Oxford University),,,Poster,http://arxiv.org/abs/2206.06340,,,, Three things everyone should know about Vision Transformers,Hugo Touvron (Facebook AI Research)*; Matthieu Cord (Sorbonne University); Alaaeldin M El-Nouby (Facebook AI Research); Jakob Verbeek (Facebook); Herve Jegou (Facebook AI Research),,,Poster,http://arxiv.org/abs/2203.09795,,,, DeiT III: Revenge of the ViT,Hugo Touvron (Facebook AI Research)*; Matthieu Cord (Sorbonne University); Herve Jegou (Facebook AI Research),,,Poster,http://arxiv.org/abs/2204.07118,,,, -Any-resolution Training for High-resolution Image Synthesis,"Lucy Chai (MIT)*; Michaël Gharbi (Adobe Research); Eli Shechtman (Adobe Research, US); Phillip Isola (MIT); Richard Zhang (Adobe)",,,Poster,http://arxiv.org/abs/2204.07156,,,, +Any-resolution Training for High-resolution Image Synthesis,"Lucy Chai (MIT)*; Michaël Gharbi (Adobe Research); Eli Shechtman (Adobe Research, US); Phillip Isola (MIT); Richard Zhang (Adobe)",,,Poster,http://arxiv.org/abs/2204.07156,,,, HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields,Kim Jun-Seong (POSTECH)*; Kim Yu-Ji (POSTECH); Moon Ye-Bin (POSTECH); Tae-Hyun Oh (POSTECH),,,Poster,,,,, "PartImageNet: A Large, High-Quality Dataset of Parts",Ju He (Johns Hopkins University)*; Shuo Yang (University of Technology Sydney); Shaokang Yang (ByteDance); Adam Kortylewski (Max Planck Institute for Informatics); Xiaoding Yuan (Johns Hopkins University); Jie-Neng Chen (Johns Hopkins University); shuai liu (ByteDance Inc.); Cheng Yang (ByteDance Inc.); Qihang Yu (Johns Hopkins University); Alan Yuille (Johns Hopkins University),,,Poster,http://arxiv.org/abs/2112.00933,https://github.com/TACJu/PartImageNet,,, -Abstracting Sketches through Simple Primitives,Stephan Alaniz (University of Tübingen)*; Massimiliano Mancini (University of Tübingen); Anjan Dutta (University of Surrey); Diego Marcos (Wageningen University); Zeynep Akata (University of Tübingen),,,Poster,http://arxiv.org/abs/2207.13543,https://github.com/ExplainableML/sketch-primitives,,, +Abstracting Sketches through Simple Primitives,Stephan Alaniz (University of Tübingen)*; Massimiliano Mancini (University of Tübingen); Anjan Dutta (University of Surrey); Diego Marcos (Wageningen University); Zeynep Akata (University of Tübingen),,,Poster,http://arxiv.org/abs/2207.13543,https://github.com/ExplainableML/sketch-primitives,,, MTTrans: Cross-Domain Object Detection with Mean Teacher Transformer,"Jinze Yu (Beihang University); Jiaming Liu (Peking University); Xiaobao Wei (Beihang University); Haoyi Zhou (Beihang University); Yohei Nakata (Panasonic Corporation); Denis A Gudovskiy (Panasonic); Tomoyuki Okuno (Panasonic); Jianxin Li (Beihang University); Kurt Keutzer (UC Berkeley); Shanghang Zhang (University of California, Berkeley)*",,,Poster,,,,, TAFIM: Targeted Adversarial Attacks against Facial Image Manipulations,Shivangi Aneja (Technical University Of Munich )*; Lev Markhasin (Sony Europe); Matthias Niessner (Technical University of Munich),,,Poster,http://arxiv.org/abs/2112.09151,,,, NeuMan: Neural Human Radiance Field from a Single Video,Wei Jiang (University of British Columbia)*; Kwang Moo Yi (University of British Columbia); Golnoosh Samei (UBC); Oncel Tuzel (Apple); Anurag Ranjan (Apple),,,Poster,http://arxiv.org/abs/2203.12575,,,, @@ -838,7 +837,7 @@ ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regulariza Granularity-aware Adaptation for Image Retrieval over Multiple Tasks,Jon Almazan (Naver Labs); Byungsoo Ko (NAVER/LINE Corp.); Geonmo Gu (NAVER corp); Diane Larlus (Naver Labs Europe); Yannis Kalantidis (NAVER LABS Europe)*,,,Poster,,,,, EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers,"Junting Pan (The Chinese University of Hong Kong); Adrian Bulat (Samsung AI Center, Cambridge); Fuwen Tan (Samsung AI Center, Cambridge); Xiatian Zhu (University of Surrey); Lukasz Dudziak (Samsung AI Center Cambridge); Hongsheng Li (The Chinese University of Hong Kong); Georgios Tzimiropoulos (Queen Mary University of London); Brais Martinez (Samsung AI Center)*",,,Poster,http://arxiv.org/abs/2205.03436,https://github.com/saic-fi/edgevit,,, Multi-Domain Multi-Definition Landmark Localization for Small Datasets,David Ferman (AI Foundation); Gaurav Bharaj (AI Foundation)*,,,Poster,http://arxiv.org/abs/2203.10358,,,, -TAVA: Template-free Animatable Volumetric Actors,Ruilong Li (UC Berkeley)*; Julian Tanke (University of Bonn); Minh P Vo (Facebook Reality Labs); Michael Zollhöfer (Facebook Reality Labs); Jürgen Gall (University of Bonn); Angjoo Kanazawa (University of California Berkeley); Christoph Lassner (Meta Reality Labs Research),,,Poster,http://arxiv.org/abs/2206.08929,,,, +TAVA: Template-free Animatable Volumetric Actors,Ruilong Li (UC Berkeley)*; Julian Tanke (University of Bonn); Minh P Vo (Facebook Reality Labs); Michael Zollhöfer (Facebook Reality Labs); Jürgen Gall (University of Bonn); Angjoo Kanazawa (University of California Berkeley); Christoph Lassner (Meta Reality Labs Research),,,Poster,http://arxiv.org/abs/2206.08929,,,, Stereo Depth Estimation with Echoes,"Chenghao Zhang (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, China)*; Kun Tian (Institute of Automation, Chinese Academy of Sciences); Bolin Ni (Institute of Automation, Chinese Academy of Sciences); Gaofeng Meng (Chinese Academy of Sciences); Bin Fan (University of Science and Technology Beijing); Zhaoxiang Zhang (Chinese Academy of Sciences, China); Chunhong Pan (Institute of Automation, Chinese Academy of Sciences)",,,Poster,,,,, EASNet:Searching Elastic and Accurate Network Architecture for Stereo Matching,Qiang Wang (Harbin Institute of Technology (Shenzhen))*; Shaohuai Shi (The Hong Kong University of Science and Technology); Kaiyong Zhao (Hong Kong Baptist University); Xiaowen Chu (Hong Kong University of Science and Technology),,,Poster,,,,, DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection,Abhinav Kumar (Michigan State University)*; Garrick Brazil (Facebook); Enrique Corona (Ford Motor Company); Armin Parchami (Ford Motor Company); Xiaoming Liu (Michigan State University),,,Poster,http://arxiv.org/abs/2207.10758,https://github.com/abhi1kumar/DEVIANT,,, @@ -859,7 +858,7 @@ Bi-level Feature Alignment for Versatile Image Translation and Manipulation,Fang Lane Detection Transformer based on Multi-frame Horizontal and Vertical Attention and Visual Transformer Module,Han Zhang (Beihang University)*; Yunchao Gu (BUAA); Xinliang Wang (BUAA); Junjun Pan (Beihang University); Minghui Wang (Beihang University),,,Poster,,,,, Label-Guided Auxiliary Training Improves 3D Object Detector,"yaomin huang (East China Normal University); Xinmei Liu (East China Normal University)*; Yichen Zhu (Midea Group); Zhiyuan Xu (Midea Group); Chaomin Shen (East China Normal University); Zhengping Che (Midea Group); Guixu Zhang (East China Normal University); Yaxin Peng (Department of Mathematics, School of Science, Shanghai University); Feifei Feng (Midea Grooup); Jian Tang (Midea Group)",,,Poster,http://arxiv.org/abs/2207.11753,,,, FedX: Unsupervised Federated Learning with Cross Knowledge Distillation,Sungwon Han (KAIST)*; Sungwon Park (KAIST); Fangzhao Wu (MSRA); Sundong Kim (Institute for Basic Science); Chuhan Wu (Tsinghua University); Xing Xie (Microsoft Research Asia); Meeyoung Cha (Institute for Basic Science),,,Poster,http://arxiv.org/abs/2207.09158,,,, -ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection,Junbo Yin (Beijing Institute of Technology); Wenguan Wang (Eidgenössische Technische Hochschule Zürich); Dingfu Zhou (Baidu); Jin Fang (Baidu ); Liangjun Zhang (baidu); Cheng-Zhong Xu (University of Macau); Jianbing Shen (Inception Institute of Artificial Intelligence)*,,,Poster,http://arxiv.org/abs/2207.12654,,,, +ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection,Junbo Yin (Beijing Institute of Technology); Wenguan Wang (Eidgenössische Technische Hochschule Zürich); Dingfu Zhou (Baidu); Jin Fang (Baidu ); Liangjun Zhang (baidu); Cheng-Zhong Xu (University of Macau); Jianbing Shen (Inception Institute of Artificial Intelligence)*,,,Poster,http://arxiv.org/abs/2207.12654,,,, Audio-Driven Stylized Gesture Generation with Flow-Based Model,"Sheng Ye (Tsinghua University)*; Yu-Hui Wen (Tsinghua University); Yanan Sun (Tsinghua University); Ying He (Nanyang Technological University); Ziyang Zhang (HUAWEI TECHNOLOGIES CO.LTD); Yaoyuan Wang (Huawei Technologies Co., Ltd.); Weihua He (Tsinghua University); Yong-Jin Liu (Tsinghua University)",,,Poster,,,,, Unsupervised Domain Adaptation for One-Stage Object Detector using Offsets to Bounding Box,Jayeon Yoo (Seoul National University); Inseop Chung (Seoul National University); Nojun Kwak (Seoul National University)*,,,Poster,http://arxiv.org/abs/2207.09656,,,, Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework,"Botao Ye (Institute of Computing Technology, Chinese Academy of Sciences)*; Hong Chang (Chinese Academy of Sciences); Bingpeng MA (University of Chinese Academy of Sciences); Shiguang Shan (Institute of Computing Technology, Chinese Academy of Sciences); Xilin Chen (Institute of Computing Technology, Chinese Academy of Sciences)",,,Poster,http://arxiv.org/abs/2203.11991,https://github.com/botaoye/OSTrack,,, @@ -869,8 +868,8 @@ Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Novel Class Discovery without Forgetting,"Joseph K J (Indian Institute of Technology, Hyderabad)*; Sujoy Paul (Google Research); Gaurav Aggarwal (Google); Soma Biswas (Indian Institute of Science, Bangalore); Piyush Rai (IIT Kanpur); Kai Han (The University of Hong Kong); Vineeth N Balasubramanian (Indian Institute of Technology, Hyderabad)",,,Poster,http://arxiv.org/abs/2207.10659,,,, Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation,ZheHan Kan (Southern University of Science and Technology); Shuoshuo Chen (Southern University of Science and Technology); Zeng Li (Southern University of Science and Technology); Zhihai He (Southern University of Science and Technology)*,,,Poster,http://arxiv.org/abs/2207.02425,,,, Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning,Damien Teney (University of Adelaide)*; Maxime Peyrard (EPFL); Ehsan M Abbasnejad (The University of Adelaide),,,Poster,http://arxiv.org/abs/2207.02598,,,, -A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning,Michael Kirchhof (University of Tübingen)*; Karsten Roth (University of Tuebingen); Zeynep Akata (University of Tübingen); Enkelejda Kasneci (University of Tuebingen),,,Poster,http://arxiv.org/abs/2207.03784,,,, -Relative Pose from SIFT Features,Daniel Barath (ETH Zürich)*; Zuzana Kukelova (Czech Technical University in Prague),,,Poster,http://arxiv.org/abs/2203.07930,,,, +A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learning,Michael Kirchhof (University of Tübingen)*; Karsten Roth (University of Tuebingen); Zeynep Akata (University of Tübingen); Enkelejda Kasneci (University of Tuebingen),,,Poster,http://arxiv.org/abs/2207.03784,,,, +Relative Pose from SIFT Features,Daniel Barath (ETH Zürich)*; Zuzana Kukelova (Czech Technical University in Prague),,,Poster,http://arxiv.org/abs/2203.07930,,,, Monocular 3D Object Reconstruction with GAN Inversion,Junzhe Zhang (Nanyang Technological University)*; Daxuan Ren (Nanyang Technological University); Zhongang Cai (SenseTime International Pte Ltd); Chai Kiat Yeo (Nanyang Technological University); Bo Dai (Shanghai AI Lab); Chen Change Loy (Nanyang Technological University),,,Poster,http://arxiv.org/abs/2207.10061,https://github.com/junzhezhang/mesh-inversion,,, PromptDet: Towards Open-vocabulary Detection using Uncurated Images,Chengjian Feng (Meituan inc.)*; Yujie Zhong (University of Oxford); Zequn Jie (Meituan inc.); Xiangxiang Chu (Meituan); Haibing Ren (Meituan Inc.); Xiaolin Wei (Meituan); Weidi Xie (Shanghai Jiao Tong University); Lin Ma (Meituan),,,Poster,http://arxiv.org/abs/2203.16513,,,, Densely Constrained Depth Estimator for Monocular 3D Object Detection,"Yingyan Li (CASIA)*; Yuntao Chen (TuSimple); Jiawei He (Institute of Automation, Chinese Academy of Sciences); Zhaoxiang Zhang (Chinese Academy of Sciences, China)",,,Poster,http://arxiv.org/abs/2207.10047,https://github.com/BraveGroup/DCD,,, @@ -894,7 +893,7 @@ UniMiSS: Universal Medical Self-Supervised Learning via Breaking Dimensionality Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation,Zhengming Zhou (NLPR-IA-CAS); Qiulei Dong (NLPR-IA-CAS)*,,,Poster,,,,, Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification,Hyungtae Lee (DEVCOM Army Research Laboratory)*; Sungmin Eum (Booz Allen Hamilton Inc.); Heesung Kwon (U.S. Army Research Laboratory),,,Poster,http://arxiv.org/abs/2207.09884,,,, Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning,Boeun Kim (Seoul National University)*; Hyung Jin Chang (University of Birmingham); Jungho Kim (KETI); Jin Young Choi (Seoul National University),,,Poster,http://arxiv.org/abs/2207.06101,https://github.com/Boeun-Kim/GL-Transformer,,, -Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoiréing,Xin Yu (The University of Hong Kong)*; Peng Dai (The University of Hong Kong); Wenbo Li (The Chinese University of Hong Kong); Lan Ma (TCL Corporate Research); Jiajun Shen (TCL Research); Jia Li (Sun Yat-Sen University); Xiaojuan Qi (The University of Hong Kong),,,Poster,,,,, +Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing,Xin Yu (The University of Hong Kong)*; Peng Dai (The University of Hong Kong); Wenbo Li (The Chinese University of Hong Kong); Lan Ma (TCL Corporate Research); Jiajun Shen (TCL Research); Jia Li (Sun Yat-Sen University); Xiaojuan Qi (The University of Hong Kong),,,Poster,https://arxiv.org/abs/2207.09935,https://github.com/CVMI-Lab/UHDM,https://huggingface.co/spaces/ECCV2022/Screen_Image_Demoireing,, Instance Contour Adjustment via Structure-driven CNN,Shuchen Weng (Peking University)*; Yi Wei (Samsung Research America Inc.); Ming-Ching Chang (University at Albany - SUNY); Boxin Shi (Peking University),,,Poster,,,,, ERDN: Equivalent Receptive Field Deformable Network for Video Deblurring,Bangrui Jiang (Tsinghua University)*; zhihuai xie (Tencent); Zhen Xia (Tencent); Songnan Li (Tencent); Shan Liu (Tencent America),,,Poster,,,,, Localizing Visual Sounds the Easy Way,Shentong Mo (Carnegie Mellon University); Pedro Morgado (CMU)*,,,Poster,http://arxiv.org/abs/2203.09324,https://github.com/stoneMo/EZ-VSL,,, @@ -911,8 +910,7 @@ Relationship Spatialization for Depth Estimation,xiaoyu xu (University of Waterl Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition,"Bo Liu (Wormpex AI Research)*; Haoxiang Li (Wormpex AI Research); Hao Kang (Wormpex AI Research); Gang Hua (Wormpex AI Research); Nuno Vasconcelos (UCSD, USA)",,,Poster,http://arxiv.org/abs/2105.00127,,,, Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models,"Chenfeng Xu (UC Berkeley)*; Shijia Yang (UC Berkeley); Tomer Galanti (Massachusetts Institute of Technology); Bichen Wu (Facebook Research); Xiangyu Yue (University of California, Berkeley); Bohan Zhai (UC Berkeley); Wei Zhan (University of California, Berkeley); Kurt Keutzer (EECS, UC Berkeley); Peter Vajda (Facebook); Masayoshi Tomizuka (University of California, Berkeley)",,,Poster,http://arxiv.org/abs/2106.04180,https://github.com/chenfengxu714/image2point,,, Visual Prompt Tuning,Menglin Jia (Cornell University)*; Luming Tang (Cornell University); Bor-Chun Chen (Facebook AI); Claire T Cardie (Cornell University); Serge Belongie (University of Copenhagen); Bharath Hariharan (Cornell University); Ser-Nam Lim (Meta AI),,,Poster,http://arxiv.org/abs/2203.12119,,,, -Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation,THEODOROS PISSAS (University College London)*; Claudio S Ravasio (King's College London (KCL)); Lyndon DaCruz (Moorfields Eye Hospital / University College London); Christos Bergeles (Kings College London),,,Poster,http://arxiv.org/abs/2203.13409,"https://github.com/RViMLab/MS_CS_ContrSeg. datasets from -natural (Cityscapes, PascalContext, ADE20K",,, +Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation,THEODOROS PISSAS (University College London)*; Claudio S Ravasio (King's College London (KCL)); Lyndon DaCruz (Moorfields Eye Hospital / University College London); Christos Bergeles (Kings College London),,,Poster,http://arxiv.org/abs/2203.13409,https://github.com/RViMLab/MS_CS_ContrSeg,,, Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion,Nobuhiko Wakai (Panasonic Corporation)*; Satoshi Sato (Panasonic Corporation); Yasunori Ishii (Panasonic Holdings); Takayoshi Yamashita (Chubu University),,,Poster,http://arxiv.org/abs/2111.12927,,,, Neural-Sim: Learning to Generate Training Data with NeRF,Yunhao Ge (University of Southern California)*; Harkirat Behl (University of Oxford); Jiashu Xu (USC); Suriya Gunasekar (Microsoft Research); Neel Joshi (MICROSOFT RESEARCH); Yale Song (FAIR); Xin Wang (Microsoft Research); Laurent Itti (University of Southern California); Vibhav Vineet (Microsoft Research),,,Poster,,,,, Word-Level Fine-Grained Story Visualization,Bowen Li (University of Oxford)*,,,Poster,http://arxiv.org/abs/2208.02341,,,, @@ -982,7 +980,7 @@ Invariant Feature Learning for Generalized Long-Tailed Classification,"Kaihua Ta Fine-Grained Visual Entailment,Christopher L Thomas (Columbia University)*; Yipeng Zhang (Columbia University); Shih-Fu Chang (Columbia University),,,Poster,http://arxiv.org/abs/2203.15704,https://github.com/SkrighYZ/FGVE,,, Sliced Recursive Transformer,"Zhiqiang Shen (Carnegie Mellon University)*; Zechun Liu (Carnegie Mellon University); Eric Xing (MBZUAI, CMU, and Petuum Inc.)",,,Poster,http://arxiv.org/abs/2111.05297,https://github.com/szq0214/SReT,,, Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval,Fan Hu (Renmin University of China); Aozhu Chen (Renmin University of China); Ziyue Wang (Renmin University of China); Fangming Zhou (Renmin University of China); Jianfeng Dong (Zhejiang Gongshang University); Xirong Li (Renmin University of China)*,,,Poster,http://arxiv.org/abs/2112.01832,,,, -Asymmetric Relation Consistency Reasoning for Video Relation Grounding,Huan Li (Xi’an Jiaotong University); Ping Wei (Xi'an Jiaotong University)*; Jiapeng Li (Xi'an Jiaotong University); Zeyu Ma (Xi'an Jiaotong University); Jiahui Shang (Xi'an Jiaotong University); Nanning Zheng (Xi'an Jiaotong University),,,Poster,,,,, +Asymmetric Relation Consistency Reasoning for Video Relation Grounding,Huan Li (Xi’an Jiaotong University); Ping Wei (Xi'an Jiaotong University)*; Jiapeng Li (Xi'an Jiaotong University); Zeyu Ma (Xi'an Jiaotong University); Jiahui Shang (Xi'an Jiaotong University); Nanning Zheng (Xi'an Jiaotong University),,,Poster,,,,, PETR: Position Embedding Transformation for Multi-View 3D Object Detection,Yingfei Liu (Megvii Technology); Tiancai Wang ( Megvii Technology)*; Xiangyu Zhang (Megvii Technology); Jian Sun (Megvii Technology),,,Poster,http://arxiv.org/abs/2203.05625,https://github.com/megvii-research/PETR,,, Contextual Text Block Detection towards Scene Text Understanding,Chuhui Xue (Nanyang Technological University); Jiaxing Huang (Nanyang Technological University); Wenqing Zhang (ByteDance); Shijian Lu (Nanyang Technological University)*; Changhu Wang (ByteDance.Inc); Song Bai (University of Oxford),,,Poster,http://arxiv.org/abs/2207.12955,,,, Structure-aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation,Jingwang Ling (Tsinghua University); Zhibo Wang (Tsinghua University); Ming Lu (Intel Labs China); Quan Wang (Sensetime); Chen Qian (SenseTime); Feng Xu (Tsinghua University)*,,,Poster,http://arxiv.org/abs/2207.09019,https://github.com/gerwang/facial-detail-manipulation,,, @@ -1033,8 +1031,8 @@ TIDEE: Tidying Up Novel Rooms using Visuo-Semantic Commonsense Priors,Gabriel Sa MOTR: End-to-End Multiple-Object Tracking with TRansformer,Fangao Zeng (Megvii Technology); Bin Dong (Megvii Technology); Yuang Zhang (Shanghai Jiao Tong University); Tiancai Wang ( Megvii Technology)*; Xiangyu Zhang (Megvii Technology); Yichen Wei (Megvii Research Shanghai),,,Poster,http://arxiv.org/abs/2105.03247,https://github.com/megvii-research/MOTR,,, K-centered Patch Sampling for Efficient Video Recognition,Seong Hyeon Park (KAIST AI)*; Jihoon Tack (KAIST); Byeongho Heo (NAVER AI LAB); Jung-Woo Ha (NAVER CLOVA AI Lab); Jinwoo Shin (KAIST),,,Poster,,,,, Learning Implicit Feature Alignment Function for Semantic Segmentation,Hanzhe Hu (Peking University)*; Yinbo Chen (UC San Diego); Jiarui Xu (University of California San Diego); Shubhankar Borse (Qualcomm AI Research ); Hong Cai (Qualcomm AI Research); Fatih Porikli (Qualcomm AI Research); Xiaolong Wang (UCSD),,,Poster,http://arxiv.org/abs/2206.08655,https://github.com/hzhupku/IFA,,, -A Visual Navigation Perspective for Category-Level Object Pose Estimation,Jiaxin Guo (Zhejiang University)*; Yiyi Liao (MPI-IS and University of Tübingen); Zhong Fangxun (CUHK); Rong Xiong (Zhejiang University); Yunhui Liu (CUHK); Yue Wang (Zhejiang University),,,Poster,http://arxiv.org/abs/2203.13572,,,, -ScaleNet: Searching for the Model to Scale,Jiyang Xie (Huawei Noah’s Ark Lab); Xiu Su (University of Sydney); Shan You (SenseTime); Zhanyu Ma (Beijing University of Posts and Telecommunications)*; Fei Wang (University of Science and Technology of China); Chen Qian (SenseTime),,,Poster,http://arxiv.org/abs/2207.07267,https://github.com/luminolx/ScaleNet,,, +A Visual Navigation Perspective for Category-Level Object Pose Estimation,Jiaxin Guo (Zhejiang University)*; Yiyi Liao (MPI-IS and University of Tübingen); Zhong Fangxun (CUHK); Rong Xiong (Zhejiang University); Yunhui Liu (CUHK); Yue Wang (Zhejiang University),,,Poster,http://arxiv.org/abs/2203.13572,,,, +ScaleNet: Searching for the Model to Scale,Jiyang Xie (Huawei Noah’s Ark Lab); Xiu Su (University of Sydney); Shan You (SenseTime); Zhanyu Ma (Beijing University of Posts and Telecommunications)*; Fei Wang (University of Science and Technology of China); Chen Qian (SenseTime),,,Poster,http://arxiv.org/abs/2207.07267,https://github.com/luminolx/ScaleNet,,, Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels,Ganlong Zhao (The University of Hong Kong); Guanbin Li (Sun Yat-sen University)*; Yipeng Qin (Cardiff University); Feng Liu (Deepwise AI Lab); Yizhou Yu (The University of Hong Kong),,,Poster,http://arxiv.org/abs/2207.14476,,,, GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing,Sijie Zhu (University of Central Florida)*; Zhe Lin (Adobe Research); Scott Cohen (Adobe Research); Jason Kuen (Adobe Research); Zhifei Zhang (Adobe Research); Chen Chen (University of Central Florida),,,Poster,http://arxiv.org/abs/2204.00125,,,, FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification,Xiaofeng Lin (University of California - Los Angeles); Seungbae Kim (University of South Florida); Jungseock Joo (University of California Los Angeles)*,,,Poster,http://arxiv.org/abs/2207.10888,https://github.com/Bernardo1998/FairGRAPE,,, @@ -1057,7 +1055,7 @@ Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectivene A Generalized & Robust Framework For Timestamp Supervision in Temporal Action Segmentation,Rahul Rahaman (National University of Singapore)*; Dipika Singhania (National University of Singapore); Alex Thiery (National University of Singapore); Angela Yao (National University of Singapore),,,Poster,http://arxiv.org/abs/2207.10137,,,, A Deep Moving-camera Background Model,Guy Erez (Ben Gurion University)*; Ron A Shapira Weber (Ben-Gurion University); Oren Freifeld (Ben-Gurion University),,,Poster,,,,, DLME: Deep Local-flatness Manifold Embedding,Zelin Zang (Zhejiang University & Westlake University)*; Siyuan Li (Westlake University); di wu (Westlake University); Ge Wang (Westlake University); Kai Wang (National University of Singapore); Lei Shang (Alibaba Group); Baigui Sun (Alibaba Group); Hao Li (Alibaba Group); Stan Z. Li (Westlake University),,,Poster,http://arxiv.org/abs/2207.03160,,,, -Neural Video Compression using GANs for Detail Synthesis and Propagation,Fabian Mentzer (Google)*; Eirikur Agustsson (Google); Johannes Ballé (Google); David Minnen (Google Inc.); Nick Johnston (Google); George Toderici (Google Research),,,Poster,http://arxiv.org/abs/2107.12038,,,, +Neural Video Compression using GANs for Detail Synthesis and Propagation,Fabian Mentzer (Google)*; Eirikur Agustsson (Google); Johannes Ballé (Google); David Minnen (Google Inc.); Nick Johnston (Google); George Toderici (Google Research),,,Poster,http://arxiv.org/abs/2107.12038,,,, Few-shot Action Recognition with Hierarchical Matching and Contrastive Learning,Sipeng Zheng (Renmin University of China)*; Shizhe Chen (INRIA); Qin Jin (Renmin University of China),,,Poster,,,,, Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation,"Yinlin Hu (EPFL)*; Pascal Fua (EPFL, Switzerland); Mathieu Salzmann (EPFL)",,,Poster,http://arxiv.org/abs/2203.09836,,,, TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information,Suraj Kothawade (UT Dallas)*; Saikat Ghosh (University of Texas at Dallas); Sumit Shekhar (Adobe Research); Yu Xiang (The University of Texas at Dallas); Rishabh Iyer (University of Texas at Dallas),,,Poster,http://arxiv.org/abs/2112.00166,,,, @@ -1069,41 +1067,41 @@ VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Vis Self-Supervised Classification Network,Elad Amrani (IBM / Technion)*; Leonid Karlinsky (IBM-Research); Alex Bronstein (Technion),,,Poster,http://arxiv.org/abs/2103.10994,https://github.com/elad-amrani/self-classifier,,, DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction,Kaichen Zhou (University of Oxford)*; Lanqing Hong (Huawei Noah's Ark Lab); Changhao Chen (National University of Defense Technology); Hang Xu (Huawei Noah's Ark Lab); Chaoqiang Ye (Huawei); Qingyong Hu (University of Oxford); Zhenguo Li (Huawei Noah's Ark Lab),,,Poster,,,,, Bayesian Optimization with Clustering and Rollback for CNN Auto Pruning,Hanwei FAN (HKUST)*; Jiandong MU (HKUST); Wei Zhang (Hong Kong University of Science and Technology),,,Poster,http://arxiv.org/abs/2109.10591,https://github.com/fanhanwei/BOCR,,, -Towards Real-World HDRTV Reconstruction: A Data Synthesis-based Approach,Zhen Cheng (University of Science and Technology of China)*; Tao Wang (Huawei Noah’s Ark Lab); Yong Li (Huawei Noah's Ark Lab); Fenglong Song (Huawei Noah's Ark Lab); Chang Chen (Huawei Noah's Ark Lab); Zhiwei Xiong (University of Science and Technology of China),,,Poster,,,,, +Towards Real-World HDRTV Reconstruction: A Data Synthesis-based Approach,Zhen Cheng (University of Science and Technology of China)*; Tao Wang (Huawei Noah’s Ark Lab); Yong Li (Huawei Noah's Ark Lab); Fenglong Song (Huawei Noah's Ark Lab); Chang Chen (Huawei Noah's Ark Lab); Zhiwei Xiong (University of Science and Technology of China),,,Poster,,,,, Quantum Motion Segmentation,Federica Arrigoni (University of Trento)*; Willi Menapace (University of Trento); Marcel Seelbach Benkner (University of Siegen); Elisa Ricci (University of Trento); Vladislav Golyanik (MPI for Informatics),,,Poster,http://arxiv.org/abs/2203.13185,,,, Open-world Semantic Segmentation via Contrasting and Clustering Vision-language Embedding,Quande Liu (The Chinese University of Hong Kong)*; Youpeng Wen (Dalian University of Technology); Jianhua Han (Huawei Noah's Ark Lab); Chunjing Xu (Huawei Noah's Ark Lab); Hang Xu (Huawei Noah's Ark Lab); Xiaodan Liang (Sun Yat-sen University),,,Poster,http://arxiv.org/abs/2207.08455,,,, -Custom Structure Preservation in Face Aging,Guillermo Gomez-Trenado (University of Granada)*; Stéphane Lathuilière (Telecom-Paris); Pablo Mesejo (University of Granada); Oscar Cordón García (University of Granada),,,Poster,http://arxiv.org/abs/2207.11025,https://github.com/guillermogotre/CUSP,,, +Custom Structure Preservation in Face Aging,Guillermo Gomez-Trenado (University of Granada)*; Stéphane Lathuilière (Telecom-Paris); Pablo Mesejo (University of Granada); Oscar Cordón García (University of Granada),,,Poster,http://arxiv.org/abs/2207.11025,https://github.com/guillermogotre/CUSP,,, DANBO: Disentangled Articulated Neural Body Representations via Graph Neural Networks,Shih-Yang Su (University of British Columbia)*; Timur Bagautdinov (Facebook); Helge Rhodin (UBC),,,Poster,http://arxiv.org/abs/2205.01666,,,, Class Is Invariant to Context and Vice Versa: On Learning Invariance for Out-Of-Distribution Generalization,"Jiaxin Qi (Nanyang Technological University)*; Kaihua Tang (Nanyang Technological University); Qianru Sun (Singapore Management University); Xian-Sheng Hua (Damo Academy, Alibaba Group); Hanwang Zhang (Nanyang Technological University)",,,Poster,http://arxiv.org/abs/2208.03462,https://github.com/simpleshinobu/IRMCon,,, Spatio-Temporal Deformable Attention Network for Video Deblurring,Huicong Zhang (Harbin Institute of Technology)*; Haozhe Xie (Tencent AI Lab); Hongxun Yao (Harbin Institute of Technology),,,Poster,http://arxiv.org/abs/2207.10852,,,, -"CHORE: Contact, Human and Object REconstruction from a single RGB image","Xianghui Xie (Saarland University )*; Bharat Lal Bhatnagar (University of Tübingen, MPI informatik); Gerard Pons-Moll (University of Tübingen)",,,Poster,http://arxiv.org/abs/2204.02445,,,, -Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction,"Vincent LE GUEN (EDF R&D, CNAM)*; Clément Rambour (Cnam); Nicolas Thome (CNAM, Paris)",,,Poster,http://arxiv.org/abs/2207.03790,,,, +"CHORE: Contact, Human and Object REconstruction from a single RGB image","Xianghui Xie (Saarland University )*; Bharat Lal Bhatnagar (University of Tübingen, MPI informatik); Gerard Pons-Moll (University of Tübingen)",,,Poster,http://arxiv.org/abs/2204.02445,,,, +Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction,"Vincent LE GUEN (EDF R&D, CNAM)*; Clément Rambour (Cnam); Nicolas Thome (CNAM, Paris)",,,Poster,http://arxiv.org/abs/2207.03790,,,, Learning Discriminative Shrinkage Deep Networks for Image Deconvolution,Pin-Hung Kuo (National Taiwan University)*; Jinshan Pan (Nanjing University of Science and Technology); Shao-Yi Chien (National Taiwan University); Ming-Hsuan Yang (University of California at Merced),,,Poster,http://arxiv.org/abs/2111.13876,,,, Camera Pose Estimation and Localization with Active Audio Sensing,Karren D Yang (MIT); Michael Firman (Niantic); Eric Brachmann (Niantic)*; Clement LJC Godard (Niantic),,,Poster,,,,, Learning Efficient Multi-Agent Cooperative Visual Exploration,Chao Yu (Tsinghua University); Xinyi Yang (Tinghua University)*; Jiaxuan Gao (Tsinghua University); Huazhong Yang (Tsinghua University); Yu Wang (Tsinghua University); Yi Wu (Tsinghua University),,,Poster,http://arxiv.org/abs/2110.05734,,,, 4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding,Yujin Chen (Technical University of Munich)*; Matthias Niessner (Technical University of Munich); Angela Dai (Technical University of Munich),,,Poster,http://arxiv.org/abs/2112.02990,,,, -Learned Vertex Descent: A New Direction for 3D Human Model Fitting,Enric Corona (IRI)*; Gerard Pons-Moll (University of Tübingen); Guillem Alenyà (IRI); Francesc Moreno (IRI),,,Poster,http://arxiv.org/abs/2205.06254,,,, +Learned Vertex Descent: A New Direction for 3D Human Model Fitting,Enric Corona (IRI)*; Gerard Pons-Moll (University of Tübingen); Guillem Alenyà (IRI); Francesc Moreno (IRI),,,Poster,http://arxiv.org/abs/2205.06254,,,, Hierarchical Semi-Supervised Contrastive Learning for Contamination-Resistant Anomaly Detection,Gaoang Wang (Zhejiang University); Yibing Zhan (JD Explore Academy); Xinchao Wang (National University of Singapore); Mingli Song (Zhejiang University)*; Klara Nahrstedt (University of Illinois at Urbana-Champaign),,,Poster,http://arxiv.org/abs/2207.11789,https://github.com/GaoangW/HSCL,,, Learning to Fit Morphable Models,Vasileios Choutas (ETH Zurich)*; Federica Bogo (Meta); Jingjing Shen (Microsoft); Julien Valentin (Microsoft),,,Poster,http://arxiv.org/abs/2111.14824,,,, Few-Shot Classification with Contrastive Learning,Zhanyuan Yang (Shenzhen University); Jinghua Wang (Harbin Institute of Technology); Yingying Zhu (Shenzhen University)*,,,Poster,,,,, ARM: Any-Time Super-Resolution Method,"Bohong Chen (Xiamen University)*; Mingbao Lin (Xiamen University, China); Kekai Sheng (Youtu Lab, Tencent Inc.); mengdan zhang (Youtu, Tencent); Peixian Chen (Youtu Tencent); Ke Li (Tencent); Liujuan Cao (Xiamen University); Rongrong Ji (Xiamen University, China)",,,Poster,http://arxiv.org/abs/2203.10812,https://github.com/chenbong/ARM-Net,,, -Tracking Every Thing in the Wild,Siyuan Li (ETH Zurich)*; Martin Danelljan (ETH Zurich); Henghui Ding (ETH Zurich); Thomas E Huang (ETH Zürich); Fisher Yu (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.12978,,,, +Tracking Every Thing in the Wild,Siyuan Li (ETH Zurich)*; Martin Danelljan (ETH Zurich); Henghui Ding (ETH Zurich); Thomas E Huang (ETH Zürich); Fisher Yu (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.12978,,,, Learning Self-prior for Mesh Denoising using Dual Graph Convolutional Networks,Shota Hattori (The University of Tokyo)*; Tatsuya Yatagawa (The University of Tokyo); Yutaka Ohtake (The University of Tokyo); Suzuki Hiromasa (The University of Tokyo),,,Poster,,,,, Few Zero Level Set-Shot Learning of Shape Signed Distance Functions in Feature Space,Amine Ouasfi (IMT Atlantique ); Adnane Boukhayma (Inria)*,,,Poster,,,,, -Attention-aware Learning for Hyperparameters Prediction in Image Processing Pipelines,"Haina Qin (University of Chinese Academy of Sciences); Longfei Han (Beijing Technology and Business University); Juan Wang (Institute of Automation, Chinese Academy of Sciences); Congxuan Zhang (Nanchang Hangkong University); Bing Li (National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences)*; Weiming Hu (Institute of Automation，Chinese Academy of Sciences); Yanwei Li (Zeku Technology(Shanghai) Corp.,Ltd.)",,,Poster,,,,, +Attention-aware Learning for Hyperparameters Prediction in Image Processing Pipelines,"Haina Qin (University of Chinese Academy of Sciences); Longfei Han (Beijing Technology and Business University); Juan Wang (Institute of Automation, Chinese Academy of Sciences); Congxuan Zhang (Nanchang Hangkong University); Bing Li (National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences)*; Weiming Hu (Institute of Automation，Chinese Academy of Sciences); Yanwei Li (Zeku Technology(Shanghai) Corp.,Ltd.)",,,Poster,,,,, Attaining Class-level Forgetting in Pretrained Model using Few Samples,Pravendra Singh (IIT Roorkee); Pratik Mazumder (Indian Institute of Technology Jodhpur)*; Mohammed Asad Karim (Carnegie Mellon University),,,Poster,,,,, -Data Invariants to Understand Unsupervised Out-of-Distribution Detection,Lars Doorenbos (University of Bern)*; Raphael Sznitman (University of Bern); Pablo Márquez Neila (University of Bern),,,Poster,http://arxiv.org/abs/2111.13362,,,, -STEEX: Steering Counterfactual Explanations with Semantics,Paul Jacob (École Polytechnique ); eloi zablocki (Valeo.ai)*; Hedi Ben-younes (Valeo AI); Mickael Chen (valeo.ai); Patrick Pérez (Valeo.ai); Matthieu Cord (Sorbonne University),,,Poster,http://arxiv.org/abs/2111.09094,https://github.com/valeoai/STEEX,,, -Outpainting by Queries,Kai Yao (Xi'an Jiaotong-liverpool University); Penglei Gao (Xi'an Jiaotong-Liverpool University); Xi Yang (Xi’an Jiaotong Liverpool University ); jie Sun (Xi'an Jiaotong-Liverpool University ); Rui Zhang (Xi'an Jiaotong-Liverpool University); Kaizhu Huang (Duke Kunshan University)*,,,Poster,http://arxiv.org/abs/2207.05312,,,, -HULC: 3D HUman Motion Capture with Pose Manifold SampLing and Dense Contact Guidance,Soshi Shimada (MPI for Informatics)*; Vladislav Golyanik (MPI for Informatics); Zhi Li (Max Planck Institute for Informatics); Patrick Pérez (Valeo.ai); Weipeng Xu (Reality Labs Research); Christian Theobalt (MPI Informatik),,,Poster,http://arxiv.org/abs/2205.05677,,,, +Data Invariants to Understand Unsupervised Out-of-Distribution Detection,Lars Doorenbos (University of Bern)*; Raphael Sznitman (University of Bern); Pablo Márquez Neila (University of Bern),,,Poster,http://arxiv.org/abs/2111.13362,,,, +STEEX: Steering Counterfactual Explanations with Semantics,Paul Jacob (École Polytechnique ); eloi zablocki (Valeo.ai)*; Hedi Ben-younes (Valeo AI); Mickael Chen (valeo.ai); Patrick Pérez (Valeo.ai); Matthieu Cord (Sorbonne University),,,Poster,http://arxiv.org/abs/2111.09094,https://github.com/valeoai/STEEX,,, +Outpainting by Queries,Kai Yao (Xi'an Jiaotong-liverpool University); Penglei Gao (Xi'an Jiaotong-Liverpool University); Xi Yang (Xi’an Jiaotong Liverpool University ); jie Sun (Xi'an Jiaotong-Liverpool University ); Rui Zhang (Xi'an Jiaotong-Liverpool University); Kaizhu Huang (Duke Kunshan University)*,,,Poster,http://arxiv.org/abs/2207.05312,,,, +HULC: 3D HUman Motion Capture with Pose Manifold SampLing and Dense Contact Guidance,Soshi Shimada (MPI for Informatics)*; Vladislav Golyanik (MPI for Informatics); Zhi Li (Max Planck Institute for Informatics); Patrick Pérez (Valeo.ai); Weipeng Xu (Reality Labs Research); Christian Theobalt (MPI Informatik),,,Poster,http://arxiv.org/abs/2205.05677,,,, Interpretable Open-Set Domain Adaptation via Angular Margin Separation,Xinhao Li (University of Electronic Science and Technology of China); Jingjing Li (University of Electronic Science and Technology of China)*; Zhekai Du (University of Electronic Science and Technology of China); Lei Zhu (Shandong Normal Unversity); Wen Li (University of Electronic Science and Technology of China),,,Poster,,,,, -EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices,Siwei Zhang (ETH Zurich)*; Qianli Ma (Max Planck Institute for Intelligent Systems); Yan Zhang (ETH Zurich); Zhiyin Qian (ETH Zürich); Taein Kwon (ETH Zurich); Marc Pollefeys (ETH Zurich / Microsoft); Federica Bogo (Meta); Siyu Tang (ETH Zurich),,,Poster,http://arxiv.org/abs/2112.07642,,,, -ViTAS: Vision Transformer Architecture Search,"Xiu Su (University of Sydney); Shan You (SenseTime)*; Jiyang Xie (Huawei Noah’s Ark Lab); Mingkai Zheng (The University of Sydney); Fei Wang (University of Science and Technology of China); Chen Qian (SenseTime); Changshui Zhang (Tsinghua University); Xiaogang Wang (Chinese University of Hong Kong, Hong Kong); Chang Xu (University of Sydney)",,,Poster,http://arxiv.org/abs/2106.13700,,,, +EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices,Siwei Zhang (ETH Zurich)*; Qianli Ma (Max Planck Institute for Intelligent Systems); Yan Zhang (ETH Zurich); Zhiyin Qian (ETH Zürich); Taein Kwon (ETH Zurich); Marc Pollefeys (ETH Zurich / Microsoft); Federica Bogo (Meta); Siyu Tang (ETH Zurich),,,Poster,http://arxiv.org/abs/2112.07642,,,, +ViTAS: Vision Transformer Architecture Search,"Xiu Su (University of Sydney); Shan You (SenseTime)*; Jiyang Xie (Huawei Noah’s Ark Lab); Mingkai Zheng (The University of Sydney); Fei Wang (University of Science and Technology of China); Chen Qian (SenseTime); Changshui Zhang (Tsinghua University); Xiaogang Wang (Chinese University of Hong Kong, Hong Kong); Chang Xu (University of Sydney)",,,Poster,http://arxiv.org/abs/2106.13700,,,, LaLaLoc++: Global Floor Plan Comprehension for Layout Localisation in Unvisited Environments,Henry Howard-Jenkins (University of Oxford)*; Victor Adrian Prisacariu (University of Oxford),,,Poster,,,,, diffConv: Analyzing Irregular Point Clouds with an Irregular View,Manxi Lin (Technical University of Denmark)*; Aasa Feragen (Technical University of Denmark),,,Poster,http://arxiv.org/abs/2111.14658,,,, ReAct: Temporal Action Detection with Relational Action Queries,Dingfeng Shi (Beihang University)*; Yujie Zhong (University of Oxford); Qiong Cao (JD.com); Jing Zhang (The University of Sydney); Lin Ma (Meituan); Jia Li (Beihang University); Dacheng Tao (JD.com),,,Poster,,https://github.com/sssste/React,,, StyleBabel: Artistic Style Tagging and Captioning,Dan Ruta (University of Surrey)*; Andrew Gilbert (University of Surrey); Pranav V Aggarwal (Adobe Inc.); Naveen Marri (Adobe Inc); Ajinkya Kale (Adobe); Jo Briggs (University of Northumbria); Chris Speed (University of Edinburgh); Hailin Jin (Adobe Research); Baldo Faieta (Adobe); Alex Filipkowski (Adobe); Zhe Lin (Adobe Research); John Collomosse (Adobe Research),,,Poster,http://arxiv.org/abs/2203.05321,,,, -TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation,RUI GONG (ETH Zurich)*; Martin Danelljan (ETH Zurich); Dengxin Dai (ETH Zurich); Danda Pani Paudel (ETH Zürich); Ajad Chhatkuli (ETH Zurich); Fisher Yu (ETH Zurich); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2109.04813,https://github.com/ETHRuiGong/TADA,,, +TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation,RUI GONG (ETH Zurich)*; Martin Danelljan (ETH Zurich); Dengxin Dai (ETH Zurich); Danda Pani Paudel (ETH Zürich); Ajad Chhatkuli (ETH Zurich); Fisher Yu (ETH Zurich); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2109.04813,https://github.com/ETHRuiGong/TADA,,, Domain Invariant Autoencoders for Self-supervised Learning from Multi-domains,Haiyang Yang (Nanjing University)*; Shixiang Tang (The University of Sydney); Meilin Chen (Zhejiang University); Yizhou Wang (Zhejiang University); Feng Zhu (University of Science and Technology of China); Lei Bai (Shanghai AI Laboratory); Rui Zhao (SenseTime Group Limited); Wanli Ouyang (The University of Sydney),,,Poster,,,,, Learned Variational Video Color Propagation,Markus Hofinger (Graz University of Technology)*; Erich Kobler (University Hospital Bonn); Alexander Effland (University of Bonn); Thomas Pock (Graz University of Technology),,,Poster,,,,, PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows,aihua mao (South China University of Technolgoy)*; Zihui Du (South China University of Technology); Yu-Hui Wen (Tsinghua University); Jun Xuan (South China University of Technology); Yong-Jin Liu (Tsinghua University),,,Poster,,,,, @@ -1116,7 +1114,7 @@ Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detec Detecting Generated Images by Real Images,Bo Liu (Chongqing University of Posts and Telecommunications); fan yang (Chongqing University of Posts and Telecommunications); Xiuli Bi (Chongqing University of Posts and Telecommunications); bin xiao (Chongqing University of Posts and Telecommunications)*; Weisheng Li (Chongqing University of Posts and Telecommunications); Xinbo Gao (Chongqing University of Posts and Telecommunications),,,Poster,,,,, VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection,Joanna Hong (KAIST)*; Minsu Kim (KAIST); Yong Man Ro (KAIST),,,Poster,http://arxiv.org/abs/2206.07458,,,, Delta Distillation for Efficient Video Processing,Amirhossein Habibian (Qualcomm AI Research)*; Haitam Ben Yahia (Qualcomm AI Research); Davide Abati (Qualcomm AI Research); Efstratios Gavves (University of Amsterdam ); Fatih Porikli (Qualcomm AI Research),,,Poster,http://arxiv.org/abs/2203.09594,,,, -PANDORA: A Panoramic Detection Dataset for Object with Orientation,"Hang Xu (Hangzhou Dianzi University;The Institute of Computing Technology of the Chinese Academy of Sciences); Qiang Zhao (The Institute of Computing Technology of the Chinese Academy of Sciences); Yike Ma (Institute of Computing Technology, Chinese Academy of Sciences); Xiaodong Li (Huawei Noah's Ark Lab); Peng Yuan (Huawei Noah’s Ark Lab); Bailan Feng (Huawei Noah's Ark Lab); Chenggang Yan (Hangzhou Dianzi University); Feng Dai (Institute of Computing Technology, Chinese Academy of Sciences)*",,,Poster,,,,, +PANDORA: A Panoramic Detection Dataset for Object with Orientation,"Hang Xu (Hangzhou Dianzi University;The Institute of Computing Technology of the Chinese Academy of Sciences); Qiang Zhao (The Institute of Computing Technology of the Chinese Academy of Sciences); Yike Ma (Institute of Computing Technology, Chinese Academy of Sciences); Xiaodong Li (Huawei Noah's Ark Lab); Peng Yuan (Huawei Noah’s Ark Lab); Bailan Feng (Huawei Noah's Ark Lab); Chenggang Yan (Hangzhou Dianzi University); Feng Dai (Institute of Computing Technology, Chinese Academy of Sciences)*",,,Poster,,,,, Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation,Feng Zhu (University of Technology Sydney)*; Zongxin Yang (Zhejiang University); Xin Yu (University of Technology Sydney); Yi Yang (Zhejiang University); Yunchao Wei (UTS),,,Poster,http://arxiv.org/abs/2208.03079,https://github.com/zfonemore/IAI,,, Audio-Visual Mismatch-Aware Video Retrieval via Association and Adjustment,Sangmin Lee (KAIST)*; Sungjune Park (KAIST); Yong Man Ro (KAIST),,,Poster,,,,, 3D Clothed Human Reconstruction in the Wild,Gyeongsik Moon (Seoul National University); Hyeongjin Nam (Seoul National University); Takaaki Shiratori (Meta Reality Labs Research); Kyoung Mu Lee (Seoul National University)*,,,Poster,http://arxiv.org/abs/2207.10053,https://github.com/hygenie1228/ClothWild_RELEASE,,, @@ -1134,7 +1132,7 @@ Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffu Contrastive Vicinal Space for Unsupervised Domain Adaptation,Jaemin Na (Ajou University)*; Dongyoon Han (NAVER AI Lab); Hyung Jin Chang (University of Birmingham); Wonjun Hwang (Ajou University),,,Poster,http://arxiv.org/abs/2111.13353,https://github.com/NaJaeMin92/CoVi,,, Weight Fixing Networks,Chris Subia-Waud (University of Southampton)*; Srinandan Dasmahapatra (University of Southampton),,,Poster,,,,, Sim-to-Real 6D Object Pose Estimation via Iterative Self-training for Robotic Bin Picking,Kai Chen (The Chinese University of Hong Kong); Rui Cao (The Chinese University of Hong Kong); Stephen L James (UC Berkeley); YICHUAN LI (CUHK); Yunhui Liu (CUHK); Pieter Abbeel (UC Berkeley); Qi Dou (The Chinese University of Hong Kong)*,,,Poster,http://arxiv.org/abs/2204.07049,,,, -ChunkyGAN: Real Image Inversion via Segments,"Adéla Šubrtová (Czech Technical University); David Futschik (Czech Technical University in Prague, FEE); Jan Čech (Czech Technical University in Prague); Michal Lukáč (Adobe Research); Eli Shechtman (Adobe Research, US); Daniel Sýkora (Czech Technical University in Prague)*",,,Poster,,,,, +ChunkyGAN: Real Image Inversion via Segments,"Adéla Å ubrtová (Czech Technical University); David Futschik (Czech Technical University in Prague, FEE); Jan ÄŒech (Czech Technical University in Prague); Michal LukáÄ� (Adobe Research); Eli Shechtman (Adobe Research, US); Daniel Sýkora (Czech Technical University in Prague)*",,,Poster,,,,, Towards Sequence-Level Training for Visual Tracking,Minji Kim (Seoul National University)*; Seungkwan Lee (POSTECH); Jungseul Ok (POSTECH); Bohyung Han (Seoul National University); Minsu Cho (POSTECH),,,Poster,http://arxiv.org/abs/2208.05810,,,, Scale-aware Spatio-temporal Relation Learning for Video Anomaly Detection,"Guoqiu Li (Tsinghua Shenzhen International Graduate School, Tsinghua University)*; Guanxiong Cai (Shenzhen SenseTime Technology Co., Ltd); Xingyu ZENG (SenseTime Group Limited); Rui Zhao (SenseTime Group Limited)",,,Poster,,,,, Tracking by Associating Clips,Sanghyun Woo (KAIST)*; Kwanyong Park (KAIST); Seoung Wug Oh (Adobe Research); In So Kweon (KAIST); Joon-Young Lee (Adobe Research),,,Poster,,,,, @@ -1152,7 +1150,7 @@ GAN Cocktail: mixing GANs without dataset access,Omri Avrahami (The Hebrew Unive Coarse-To-Fine Incremental Few-Shot Learning,Xiang Xiang (Huazhong University of Science and Technology)*; Yuwen Tan (Huazhong University of Science and Technology); Qian Wan (Wuhan Research Institute of Posts and Telecommunications); Jing Ma (Huazhong University of Science and Technology); Alan Yuille (Johns Hopkins University); Gregory D. Hager (The Johns Hopkins University),,,Poster,http://arxiv.org/abs/2111.14806,,,, Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling,Jian Hu (Queen Mary University of London)*; Haowen Zhong (Zhejiang Lab); Fei Yang (Zhejiang Lab); Shaogang Gong (Queen Mary University of London); Guile Wu (Queen Mary University of London); Junchi Yan (Shanghai Jiao Tong University),,,Poster,http://arxiv.org/abs/2206.01319,,,, Camera Pose Auto-Encoders for Improving Pose Regression,"Yoli Shavit (Faculty of Engineering, Bar Ilan University); Yosi Keller (Bar Ilan University)*",,,Poster,http://arxiv.org/abs/2207.05530,https://github.com/yolish/camera-pose-auto-encoders,,, -CoGS: Controllable Generation and Search from Sketch and Style,"Cusuh Ham (Georgia Institute of Technology)*; Gemma Canet Tarrés (CVSSP, University of Surrey); Tu Bui (University of Surrey); James Hays (Georgia Institute of Technology, USA); Zhe Lin (Adobe Research); John Collomosse (Adobe Research)",,,Poster,http://arxiv.org/abs/2203.09554,,,, +CoGS: Controllable Generation and Search from Sketch and Style,"Cusuh Ham (Georgia Institute of Technology)*; Gemma Canet Tarrés (CVSSP, University of Surrey); Tu Bui (University of Surrey); James Hays (Georgia Institute of Technology, USA); Zhe Lin (Adobe Research); John Collomosse (Adobe Research)",,,Poster,http://arxiv.org/abs/2203.09554,,,, Active Audio-Visual Separation of Dynamic Sound Sources,Sagnik Majumder (University of Texas at Austin)*; Kristen Grauman (Facebook AI Research & UT Austin),,,Poster,http://arxiv.org/abs/2202.00850,,,, AU-aware 3D Face Reconstruction through Personalized AU-specific Blendshape Learning,"Chenyi Kuang (Rensselaer Polytechnic Institute)*; Zijun Cui (Rensselaer Polytechnic Institute); Jeffrey Kephart (IBM Research, USA); Qiang Ji (Renselaer Polytechnic Institute)",,,Poster,,,,, Directed Ray Distance Functions for 3D Scene Reconstruction,Nilesh Kulkarni (University of Michigan)*; Justin Johnson (University of Michigan); David Fouhey (University of Michigan),,,Poster,,,,, @@ -1165,7 +1163,7 @@ FindIt: Generalized Localization with Natural Language Queries,Weicheng Kuo (Goo SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data,David M Hart (Brigham Young University)*; Michael Whitney (Brigham Young University); Bryan S Morse (Brigham Young University),,,Poster,http://arxiv.org/abs/2207.08979,,,, HairNet: Hairstyle Transfer with Pose Changes,Peihao Zhu (KAUST)*; Rameen Abdal (KAUST); JOHN C FEMIANI (Miami University); Peter Wonka (KAUST),,,Poster,,,,, Learn2Augment: Learning to Composite Videos for Data Augmentation in Action Recognition,Shreyank N Gowda (University of Edinburgh)*; Marcus Rohrbach (Facebook AI Research); Frank Keller (University of Edinburgh); Laura Sevilla-Lara (Facebook),,,Poster,http://arxiv.org/abs/2206.04790,,,, -Action-based Contrastive Learning for Trajectory Prediction,Marah Halawa (Technische Universität Berlin)*; Olaf Hellwich (Technical University Berlin); Pia Bideau (TU Berlin),,,Poster,http://arxiv.org/abs/2207.08664,,,, +Action-based Contrastive Learning for Trajectory Prediction,Marah Halawa (Technische Universität Berlin)*; Olaf Hellwich (Technical University Berlin); Pia Bideau (TU Berlin),,,Poster,http://arxiv.org/abs/2207.08664,,,, Scaling Open-vocabulary Image Segmentation with Image-level Labels,Golnaz Ghiasi (Google Brain)*; Xiuye Gu (Google); Yin Cui (Google); Tsung-Yi Lin (Nvidia Research),,,Poster,http://arxiv.org/abs/2112.12143,,,, Improving Closed and Open-Vocabulary Attribute Prediction using Transformers,"Khoi Pham (University of Maryland, College Park)*; Kushal Kafle (Adobe Research); Zhe Lin (Adobe Research); Zhihong Ding (Adobe Research); Scott Cohen (Adobe Research); Quan Hung Tran (Adobe Research); Abhinav Shrivastava (University of Maryland)",,,Poster,,,,, FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context,Pinaki Nath Chowdhury (University of Surrey)*; Aneeshan Sain (University of Surrey); Ayan Kumar Bhunia (University of Surrey); Tao Xiang (University of Surrey); Yulia Gryaditskaya (University of Surrey); Yi-Zhe Song (University of Surrey),,,Poster,,,,, @@ -1193,14 +1191,14 @@ PT4AL: Using Self-Supervised Pretext Tasks for Active Learning,John Seon Keun Yi Uncertainty Quantification in Depth Estimation via Constrained Ordinal Regression,Dongting Hu (The University of Melbourne); Liuhua Peng (The University of Melbourne); Tingjin Chu (University of Melbourne); Xiaoxing Zhang (Meituan); Yinian Mao (Meituan-Dianping Group ); Howard Bondell (University of Melbourne); Mingming Gong (University of Melbourne)*,,,Poster,,,,, All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelines,Yuxuan Zhang (Princeton University)*; Bo Dong (Princeton University); Felix Heide (Princeton University),,,Poster,http://arxiv.org/abs/2112.09219,,,, ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer,Haokui Zhang (Lighthouse Co.Ltd)*; Wenze Hu (Lighthouse Co.Ltd); Xiaoyu Wang (The Chinese University of Hong Kong (Shenzhen)),,,Poster,,,,, -B ́ezierPalm: A Free lunch for Palmprint Recognition,KAI ZHAO (UCLA)*; Lei Shen (Tencent); Yingyi Zhang (Tencent); Chuhan Zhou (Tencent & VIA University College); Tao Wang (Tencent YouTu Lab); Ruixin Zhang (Tencent); Shouhong Ding (Tencent); Wei Jia (Heifei University of Technology); Wei Shen (Shanghai Jiao Tong University),,,Poster,,,,, +B Ì�ezierPalm: A Free lunch for Palmprint Recognition,KAI ZHAO (UCLA)*; Lei Shen (Tencent); Yingyi Zhang (Tencent); Chuhan Zhou (Tencent & VIA University College); Tao Wang (Tencent YouTu Lab); Ruixin Zhang (Tencent); Shouhong Ding (Tencent); Wei Jia (Heifei University of Technology); Wei Shen (Shanghai Jiao Tong University),,,Poster,,,,, A Repulsive Force Unit for Garment Collision Handling in Neural Networks,Qingyang Tan (UMD)*; Yi Zhou (Adobe Research); Tuanfeng Wang (adobe research); Duygu Ceylan (Adobe Research); Xin Sun (Adobe Research); Dinesh Manocha (University of Maryland at College Park),,,Poster,http://arxiv.org/abs/2207.13871,,,, CYBORGS: Contrastively Bootstrapping Object Representations by Grounding in Segmentation,Renhao Wang (Tsinghua University)*; Hang Zhao (Tsinghua University); Yang Gao (Tsinghua University),,,Poster,http://arxiv.org/abs/2203.09343,,,, Connecting Compression Spaces withTransformer for Approximate Nearest Neighbor Search,"Haokui Zhang (Lighthouse Co.Ltd)*; Buzhou Tang (Harbin Institute of Technology, China); Wenze Hu (Lighthouse Co.Ltd); Xiaoyu Wang (The Chinese University of Hong Kong (Shenzhen))",,,Poster,,,,, Training Vision Transformers with Only 2040 Images,Yunhao Cao (Nanjing University); Hao Yu (Nanjing University); Jianxin Wu (Nanjing University)*,,,Poster,http://arxiv.org/abs/2201.10728,,,, Black-box Few-shot Knowledge Distillation,"Dang Nguyen (Deakin University)*; Sunil Gupta (Deakin University, Australia); Kien Duc Do (Deakin Unviersity); Svetha Venkatesh (Deakin University)",,,Poster,http://arxiv.org/abs/2207.12106,https://github.com/nphdang/FS-BBT,,, -AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling,Ziqian Bai (Simon Fraser University)*; Timur Bagautdinov (Facebook); Javier Romero (Facebook); Michael Zollhöfer (Facebook Reality Labs); Ping Tan (Simon Fraser University); Shunsuke Saito (Facebook),,,Poster,http://arxiv.org/abs/2203.13817,,,, -Ghost-free High Dynamic Range Imaging with Context-aware Transformer,Zhen Liu (Sichuan University; Megvii ); Yinglong Wang (Huawei Noah’s Ark Lab); Bing Zeng (University of Electronic Science and Technology of China); Shuaicheng Liu (UESTC; Megvii)*,,,Poster,http://arxiv.org/abs/2208.05114,https://github.com/megvii-research/HDR-Transformer,,, +AutoAvatar: Autoregressive Neural Fields for Dynamic Avatar Modeling,Ziqian Bai (Simon Fraser University)*; Timur Bagautdinov (Facebook); Javier Romero (Facebook); Michael Zollhöfer (Facebook Reality Labs); Ping Tan (Simon Fraser University); Shunsuke Saito (Facebook),,,Poster,http://arxiv.org/abs/2203.13817,,,, +Ghost-free High Dynamic Range Imaging with Context-aware Transformer,Zhen Liu (Sichuan University; Megvii ); Yinglong Wang (Huawei Noah’s Ark Lab); Bing Zeng (University of Electronic Science and Technology of China); Shuaicheng Liu (UESTC; Megvii)*,,,Poster,http://arxiv.org/abs/2208.05114,https://github.com/megvii-research/HDR-Transformer,,, Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations,"Wentao Chen (University of Science and Technology of China)*; Zhang Zhang (Institute of Automation, Chinese Academy of Sciences); Wei Wang (Institute of Automation Chinese Academy of Sciences); Liang Wang (NLPR, China); Zilei Wang (University of Science and Technology of China); Tieniu Tan (NLPR, China)",,,Poster,http://arxiv.org/abs/2207.07826,https://github.com/WentaoChen0813/CDCS-FSL,,, Motion Transformer for Unsupervised Image Animation,Jiale Tao (University of Electronic Science and Technology of China)*; Biao Wang (Alibaba Group); Tiezheng Ge (Alibaba Group); Yuning Jiang (Alibaba Group); Wen Li (University of Electronic Science and Technology of China); Lixin Duan (University of Electronic Science and Technology of China),,,Poster,,,,, LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection,Yi Wei (Tsinghua University)*; Zibu Wei (Tsinghua University); Yongming Rao (Tsinghua University); Jiaxin Li (Gaussian Robotics); Jie Zhou (Tsinghua University); Jiwen Lu (Tsinghua University),,,Poster,http://arxiv.org/abs/2203.14956,,,, @@ -1232,11 +1230,11 @@ Mutually Reinforcing Structure with Proposal Contrastive Consistency for Few-Sho Panoptic-PartFormer: Learning a Unified model for Panoptic Part Segmentation,Xiangtai Li (Peking University)*; Shilin Xu (Peking University); Yibo Yang (Peking University); Guangliang Cheng (Sensetime Group Limited); Yunhai Tong (Peking University); Dacheng Tao (JD.com),,,Poster,,,,, TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers,Oren Nuriel (Amazon)*; Ron Litman (Amazon); Sharon Fogel (Amazon),,,Poster,http://arxiv.org/abs/2105.03906,https://github.com/amazon-research/textadain-robust-recognition,,, Speaker-adaptive Lip Reading with User-dependent Padding,Minsu Kim (KAIST)*; Hyunjun Kim (KAIST); Yong Man Ro (KAIST),,,Poster,http://arxiv.org/abs/2208.04498,,,, -Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions,Theodoros Panagiotakopoulos (KTH Royal Institute of Technology in Stockholm); Pier Luigi Dovesi (Univrses); Linus Härenstam-Nielsen (Artisense); Matteo Poggi (University of Bologna)*,,,Poster,http://arxiv.org/abs/2207.10667,,,, +Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions,Theodoros Panagiotakopoulos (KTH Royal Institute of Technology in Stockholm); Pier Luigi Dovesi (Univrses); Linus Härenstam-Nielsen (Artisense); Matteo Poggi (University of Bologna)*,,,Poster,http://arxiv.org/abs/2207.10667,,,, Point Scene Understanding via Disentangled Instance Mesh Reconstruction,Jiaxiang Tang (Peking University)*; Xiaokang Chen (Peking University); Jingbo Wang (The Chinese University of HongKong); Gang Zeng (Peking University),,,Poster,http://arxiv.org/abs/2203.16832,https://github.com/ashawkey/dimr,,, Dual Contrastive Learning with Anatomical Auxiliary Supervision for Few-shot Medical Image Segmentation,Huisi Wu (Shenzhen University)*; Fangyan Xiao (Shenzhen University); Chongxin Liang (Shenzhen University),,,Poster,,,,, An Efficient Person Clustering Algorithm for Open Checkout-free Groceries,Junde Morsen Wu (Purdue University); Yu Zhang (Harbin Institute of Technology); RAO FU (None); Yuanpei Liu (Beijing Institute of Technology); Jing Gao (Purdue University)*,,,Poster,http://arxiv.org/abs/2208.02973,,,, -Face2Face^ρ: Real-Time High-Resolution One-Shot Face Reenactment,Kewei Yang (NetEase Games AI Lab)*; Kang Chen (NetEase Games AI Lab); Daoliang Guo (NetEase Games AI Lab); Song-Hai Zhang (Tsinghua University); Yuan-Chen Guo (Tsinghua University); Weidong Zhang (Netease Games AI Lab),,,Poster,,,,, +Face2Face^Ï�: Real-Time High-Resolution One-Shot Face Reenactment,Kewei Yang (NetEase Games AI Lab)*; Kang Chen (NetEase Games AI Lab); Daoliang Guo (NetEase Games AI Lab); Song-Hai Zhang (Tsinghua University); Yuan-Chen Guo (Tsinghua University); Weidong Zhang (Netease Games AI Lab),,,Poster,,,,, Decoupled Contrastive Learning,"Chun-Hsiao Yeh (Academia Sinica / UC Berkeley)*; Cheng-Yao Hong (Academia Sinica); Yen-Chi Hsu (Academia Sinica); Tyng-Luh Liu (Academia Sinica); Yubei Chen (Berkeley AI Research, UC Berkeley); yann lecun (Facebook)",,,Poster,http://arxiv.org/abs/2110.06848,,,, Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning,"Chi Zhang (University of California, Los Angeles)*; Sirui Xie (UCLA); Baoxiong Jia (UCLA); Ying Nian Wu (University of California, Los Angeles); Song-Chun Zhu (UCLA); Yixin Zhu (Peking University)",,,Poster,http://arxiv.org/abs/2111.12990,,,, On the Robustness of Quality Measures for GANs,Motasem Alfarra (KAUST)*; Juan C Perez (KAUST); Anna Fruehstueck (KAUST); Philip Torr (University of Oxford); Peter Wonka (KAUST); Bernard Ghanem (KAUST),,,Poster,http://arxiv.org/abs/2201.13019,,,, @@ -1249,8 +1247,8 @@ Style-Guided Shadow Removal,Jin Wan (Beijing Jiaotong University); Hui Yin (Beij Sound-guided Semantic Video Generation,Seung Hyun Lee (Korea University)*; Gyeongrok Oh (Korea University); Wonmin Byeon (NVIDIA Research); Jihyun Bae (Korea University); Chanyoung Kim (Korea University); Won Jeong Ryoo (Korea University); Sang Ho Yoon (KAIST); Hyunjun Cho (Korea University); Jinkyu Kim (Korea University); Sangpil Kim (Korea University),,,Poster,http://arxiv.org/abs/2204.09273,,,, Robust Visual Tracking by Segmentation,Matthieu Paul (ETH Zurich)*; Martin Danelljan (ETH Zurich); Christoph Mayer (ETH Zurich); Luc Van Gool (ETH Zurich),,,Poster,http://arxiv.org/abs/2203.11191,,,, Semi-Supervised Learning of Optical Flow by Flow Supervisor,Woobin Im (KAIST); Sebin Lee (KAIST); Sungeui Yoon (KAIST)*,,,Poster,http://arxiv.org/abs/2207.10314,https://github.com/iwbn/flow-supervisor,,, -Joint Learning of Localized Representations from Medical Images and Reports,Philip Müller (Technical University of Munich)*; Georgios Kaissis (Technische Universität München); congyu zou (Klinikum Rechts der Isar Technische Universität München ); Daniel Rueckert (Technische Universität München),,,Poster,http://arxiv.org/abs/2112.02889,,,, -D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution,Youwei Li (Megvii); Haibin Huang (Kuaishou Technology); lanpeng jia (GWM); Haoqiang Fan (Megvii Inc（face++）); Shuaicheng Liu (UESTC; Megvii)*,,,Poster,,,,, +Joint Learning of Localized Representations from Medical Images and Reports,Philip Müller (Technical University of Munich)*; Georgios Kaissis (Technische Universität München); congyu zou (Klinikum Rechts der Isar Technische Universität München ); Daniel Rueckert (Technische Universität München),,,Poster,http://arxiv.org/abs/2112.02889,,,, +D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution,Youwei Li (Megvii); Haibin Huang (Kuaishou Technology); lanpeng jia (GWM); Haoqiang Fan (Megvii Inc（face++）); Shuaicheng Liu (UESTC; Megvii)*,,,Poster,,,,, Continual 3D Convolutional Neural Networks for Real-time Processing of Videos,Lukas Hedegaard (Aarhus University)*; Alexandros Iosifidis (Aarhus University),,,Poster,http://arxiv.org/abs/2106.00050,,,, Salient Object Detection for Point Clouds,"Songlin Fan (Peking University ); Wei Gao (SECE, Shenzhen Graduate School, Peking University)*; Ge Li (Peking University)",,,Poster,http://arxiv.org/abs/2207.11889,,,, Deep ensemble learning by diverse knowledge distillation for fine-grained object classification,Naoki Okamoto (Chubu university)*; Tsubasa Hirakawa (Chubu University); Takayoshi Yamashita (Chubu University); Hironobu Fujiyoshi (Chubu University),,,Poster,,,,, @@ -1258,27 +1256,27 @@ Source-free Video Domain Adaptation by Learning Temporal Consistency for Action GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training,Jaeseok Byun (Seoul National university); Taebaek Hwang (M.IN.D Lab); Jianlong Fu (Microsoft Research); Taesup Moon (Seoul National University)*,,,Poster,,,,, Pose Forecasting in Industrial Human-Robot Collaboration,Alessio Sampieri (Sapienza University)*; Guido Maria D'Amely di Melendugno (Sapienza University); ANDREA AVOGARO (University of Verona); Federico Cunico (University of Verona); Francesco Setti (University of Verona); Geri Skenderi (University of Verona); Marco Cristani (University of Verona); Fabio Galasso (Sapienza University),,,Poster,http://arxiv.org/abs/2208.07308,,,, MeshLoc: Mesh-Based Visual Localization,"Vojtech Panek (CTU in Prague, FEE, CIIRC)*; Zuzana Kukelova (Czech Technical University in Prague); Torsten Sattler (Czech Technical University in Prague)",,,Poster,http://arxiv.org/abs/2207.10762,,,, -Dress Code: High-Resolution Multi-Category Virtual Try-On,Davide Morelli (UNIMORE); Matteo Fincato (Università degli Studi di Modena e Reggio Emilia); Marcella Cornia (University of Modena and Reggio Emilia)*; Federico Landi (University of Modena and Reggio Emilia); Fabio Cesari (YOOX Net-A-Porter Group S.p.A.); Rita Cucchiara (Università di Modena e Reggio Emilia),,,Poster,http://arxiv.org/abs/2204.08532,https://github.com/aimagelab/dress-code,,, +Dress Code: High-Resolution Multi-Category Virtual Try-On,Davide Morelli (UNIMORE); Matteo Fincato (Università degli Studi di Modena e Reggio Emilia); Marcella Cornia (University of Modena and Reggio Emilia)*; Federico Landi (University of Modena and Reggio Emilia); Fabio Cesari (YOOX Net-A-Porter Group S.p.A.); Rita Cucchiara (Università di Modena e Reggio Emilia),,,Poster,http://arxiv.org/abs/2204.08532,https://github.com/aimagelab/dress-code,,, UC-OWOD: Unknown-Classified Open World Object Detection,"Zhiheng Wu (Institute of Automation, Chinese Academy of Sciences (CASIA))*; Yue Lu (Institute of Automation, Chinese Academy of Sciences(CASIA)); Xingyu Chen (Xiaobing.AI); Zhengxing Wu (CASIA); Liwen Kang (Institute of Automation, Chinese Academy of Sciences (CASIA)); Junzhi Yu (CASIA)",,,Poster,,,,, Helpful or Harmful: Inter-Task Association in Continual Learning,Hyundong Jin (Chung-Ang University ); Eunwoo Kim (Chung-Ang University)*,,,Poster,,,,, -RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers,Michał J Tyszkiewicz (EPFL); Kevis-Kokitsi Maninis (Google Research)*; Stefan Popov (Google Research); Vittorio Ferrari (Google Research),,,Poster,http://arxiv.org/abs/2203.13296,,,, +RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers,MichaÅ‚ J Tyszkiewicz (EPFL); Kevis-Kokitsi Maninis (Google Research)*; Stefan Popov (Google Research); Vittorio Ferrari (Google Research),,,Poster,http://arxiv.org/abs/2203.13296,,,, Efficient Point Cloud Segmentation with Geometry-aware Sparse Networks,Maosheng Ye (HKUST)*; Rui Wan (Deeproute.ai); Shuangjie Xu (HKUST); Tongyi Cao (Deeproute.ai); Qifeng Chen (HKUST),,,Poster,,,,, Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition,Tianjiao Li (Singapore University of Technology and Design)*; Lin Geng Foo (Singapore University of Technology and Design); Qiuhong Ke (Monash University); Hossein Rahmani (Lancaster University); Anran Wang (Bytedance); Jinghua Wang (Harbin Institute of Technology); Jun Liu (Singapore University of Technology and Design),,,Poster,,,,, TISE: Bag of Metrics for Text-to-Image Synthesis Evaluation,Tan Minh Dinh (VinAI Research)*; Rang NGUYEN (VinAI Research); Binh-Son Hua (VinAI Research),,,Poster,http://arxiv.org/abs/2112.01398,,,, CostDCNet: Cost Volume based Depth Completion for a Single RGB-D Image,Jaewon Kam (POSTECH); Jungeon Kim (POSTECH); Soongjin Kim (POSTECH); Jaesik Park (POSTECH); Seungyong Lee (POSTECH)*,,,Poster,,,,, Efficient Video Deblurring Guided by Motion Magnitude,Yusheng Wang (The University of Tokyo)*; Yunfan Lu (Hong Kong University of Science and Technology); Ye Gao (Honor Technologies Japan); Lin Wang (HKUST); Zhihang Zhong (The University of Tokyo); Yinqiang Zheng (The University of Tokyo); Atsushi Yamashita (The University of Tokyo),,,Poster,http://arxiv.org/abs/2207.13374,,,, -Space-Partitioning RANSAC,Daniel Barath (ETH Zürich)*; Gábor Valasek (ELTE),,,Poster,http://arxiv.org/abs/2111.12385,,,, +Space-Partitioning RANSAC,Daniel Barath (ETH Zürich)*; Gábor Valasek (ELTE),,,Poster,http://arxiv.org/abs/2111.12385,,,, Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies,Xingrun Xing (Beihang University); Yangguang Li (SenseTime Group Limited); Wei Li (Nanyang Technological University); Wenrui Ding (Beihang University); Yalong Jiang (Beihang University)*; Yufeng Wang (Beihang University); Jing Shao (Sensetime); Chunlei Liu (Beihang University); Xianglong Liu (BUAA),,,Poster,,,,, Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain,Piyapat Saranrittichai (Bosch Center for Artificial Intelligence)*; Chaithanya Kumar Mummadi (Bosch Center for Artificial Intelligence); Claudia Blaiotta (Bosch Center for Artificial Intelligence); Mauricio Munoz (Bosch Center for Artificial Intelligence); Volker Fischer (Bosch Center for Artificial Intelligence),,,Poster,http://arxiv.org/abs/2207.10002,,,, SimpleRecon: 3D Reconstruction Without 3D Convolutions,"Mohamed Sayed (University College London)*; John Gibson (Niantic, Inc.); Jamie Watson (Niantic); Victor A Prisacariu (Niantic Labs); Michael Firman (Niantic); Clement LJC Godard (Niantic)",,,Poster,,,,, SemAug: Semantically Meaningful Image Augmentations for Object Detection Through Language Grounding,"Morgan L Heisler (Huawei Technologies Canada Co., Ltd.)*; Amin Banitalebi-Dehkordi (Huawei Technologies Canada Co., Ltd.); Yong Zhang (Huawei Technologies Canada Co., Ltd.)",,,Poster,http://arxiv.org/abs/2208.07407,,,, -A data-centric approach for improving ambiguous labels with combined semi-supervised classification and clustering,Lars Schmarje (Kiel University)*; Monty Santarossa (Kiel University); Simon-Martin Schröder (Kiel University); Claudius Zelenka (Kiel University); Rainer Kiko (Laboratoire d'Océanographie de Villefranche-sur-Mer); Jenny Stracke (University of Bonn); Nina Volkmann (University of Veterinary Medicine Hannover); Reinhard Koch (Kiel University),,,Poster,http://arxiv.org/abs/2106.16209,,,, +A data-centric approach for improving ambiguous labels with combined semi-supervised classification and clustering,Lars Schmarje (Kiel University)*; Monty Santarossa (Kiel University); Simon-Martin Schröder (Kiel University); Claudius Zelenka (Kiel University); Rainer Kiko (Laboratoire d'Océanographie de Villefranche-sur-Mer); Jenny Stracke (University of Bonn); Nina Volkmann (University of Veterinary Medicine Hannover); Reinhard Koch (Kiel University),,,Poster,http://arxiv.org/abs/2106.16209,,,, SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks,"Anish J Prabhu (Apple)*; Chien-Yu lin (University of Washington); Thomas Merth (Apple); Sachin Mehta (University of Washington); Anurag Ranjan (Apple); Maxwell C Horton (Apple, Xnor.Ai and University of Washington); Mohammad Rastegari (University of Washington)",,,Poster,http://arxiv.org/abs/2207.10237,https://github.com/apple/ml-spin,,, SAGA: Stochastic Whole-Body Grasping With Contact,Yan Wu (ETH Zurich); Jiahao Wang (Max Planck Institute for Informatics); Yan Zhang (ETH Zurich); Siwei Zhang (ETH Zurich); Otmar Hilliges (ETH Zurich); Fisher Yu (ETH Zurich); Siyu Tang (ETH Zurich)*,,,Poster,http://arxiv.org/abs/2112.10103,,,, GTCaR: Graph Transformer for Camera Re-localization,Xinyi Li (Magic Leap)*; Haibin Ling (Stony Brook University),,,Poster,,,,, Actor-centered Representations for Action Localization in Streaming Videos,"Sathyanarayanan N Aakur (OK State)*; Sudeep Sarkar (University of South Florida, Tampa)",,,Poster,,,,, -Photo-realistic Neural Domain Randomization,Sergey Zakharov (Toyota Research Institute)*; Rareș A Ambruș (Toyota Research Institute); Vitor Guizilini (Toyota Research Institute); Wadim Kehl (Woven Planet); Adrien Gaidon (Toyota Research Institute),,,Poster,,,,, -"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization",Muhammad Zubair Irshad (Georgia Institute of Technology)*; Sergey Zakharov (Toyota Research Institute); Rareș A Ambruș (Toyota Research Institute); Thomas Kollar (Toyota Research Institute); Zsolt Kira (Georgia Institute of Technology); Adrien Gaidon (Toyota Research Institute),,,Poster,http://arxiv.org/abs/2207.13691,,,, +Photo-realistic Neural Domain Randomization,Sergey Zakharov (Toyota Research Institute)*; RareÈ™ A AmbruÈ™ (Toyota Research Institute); Vitor Guizilini (Toyota Research Institute); Wadim Kehl (Woven Planet); Adrien Gaidon (Toyota Research Institute),,,Poster,,,,, +"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization",Muhammad Zubair Irshad (Georgia Institute of Technology)*; Sergey Zakharov (Toyota Research Institute); RareÈ™ A AmbruÈ™ (Toyota Research Institute); Thomas Kollar (Toyota Research Institute); Zsolt Kira (Georgia Institute of Technology); Adrien Gaidon (Toyota Research Institute),,,Poster,http://arxiv.org/abs/2207.13691,,,, Structure and Motion for Casual Videos,Zhoutong Zhang (MIT)*; Forrester Cole (Google Research); Zhengqi Li (Google Inc.); Noah Snavely (Google); Michael Rubinstein (Google); William T Freeman (Google),,,Poster,,,,, Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model,"Zhiyuan Mao (Purdue University)*; AJAY KUMAR JAISWAL (UT Austin); Zhangyang Wang (University of Texas at Austin); Stanley Chan (Purdue University, USA)",,,Poster,http://arxiv.org/abs/2207.10040,,,, Incremental Task Learning with Incremental Rank Updates,"Rakib Hyder (University of California, Riverside)*; Ken Shao (UCR); Boyu Hou (The University of California, Riverside ); Panagiotis Markopoulos (RIT); Ashley Prater-Bennette (Air Force Research Laboratory); M. Salman Asif (University of California, Riverside)",,,Poster,http://arxiv.org/abs/2207.09074,https://github.com/CSIPlab/task-increment-rank-update.git,,, @@ -1317,17 +1315,17 @@ When Deep Classifiers Agree: Analyzing Correlations between Learning Order and I S2F2: Single-Stage Flow Forecasting for Future Multiple Trajectories Prediction,YU-WEN CHEN (National Tsing Hua University); Hsuan-Kung Yang (National Tsing Hua University); Chu-Chi Chiu (National Tsin-Hua University); Chun-Yi Lee (National Tsing Hua University)*,,,Poster,,,,, Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations,"Wenjie Pei (Harbin Institute of Technology, Shenzhen); Shuang Wu (Harbin Institute of Technology, Shenzhen); Dianwen Mei (Harbin Institute of Technology, Shenzhen); Fanglin Chen (Harbin Institute of Technology, Shenzhen); Jiandong Tian (CAS); Guangming Lu ( Harbin Institute of Technology, Shenzhen)*",,,Poster,http://arxiv.org/abs/2207.12049,,,, Stochastic Consensus: Enhancing Semi-Supervised Learning with Consistency of Stochastic Classifiers,Hui Tang (South China University of Technology)*; Kui Jia (South China University of Technology); Lin Sun (Magic Leap),,,Poster,,,,, -Learning Where To Look – Generative NAS is Surprisingly Efficient,Jovita Lukasik (University of Mannheim)*; Steffen Jung (MPII); Margret Keuper (University of Mannheim),,,Poster,,,,, +Learning Where To Look – Generative NAS is Surprisingly Efficient,Jovita Lukasik (University of Mannheim)*; Steffen Jung (MPII); Margret Keuper (University of Mannheim),,,Poster,,,,, Realistic One-shot Mesh-based Head Avatars,Taras Khakhulin (Skolkovo Institute of Science and Technology)*; Vanessa Valerievna Skliarova (Skoltech); Victor Lempitsky (Yandex); Egor Zakharov (Skolkovo Institute of Science and Technology),,,Poster,http://arxiv.org/abs/2206.08343,,,, Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning,Seunghyun Lee (Inha University); Byung Cheol Song (Inha University)*,,,Poster,http://arxiv.org/abs/2203.02651,https://github.com/sseung0703/EKG,,, SALISA: Saliency-based Input Sampling for Efficient Video Object Detection,Babak Ehteshami Bejnordi (Qualcomm AI Reseach)*; Amir Ghodrati (Qualcomm AI Research); Fatih Porikli (Qualcomm AI Research); Amirhossein Habibian (Qualcomm AI Research),,,Poster,http://arxiv.org/abs/2204.02397,,,, -Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer,Omkar Thawakar (MBZUAI)*; Sanath Narayan (Inception Institute of Artificial Intelligence); Jiale Cao (Tianjin University); Hisham Cholakkal (MBZUAI); Rao Muhammad Anwer (MBZUAI/AALTO); Muhammad Haris Khan (Muhammad Bin Zayed University of Artificial Intelligence); Salman Khan (MBZUAI/ANU); Michael Felsberg (Linköping University); Fahad Shahbaz Khan (MBZUAI),,,Poster,http://arxiv.org/abs/2203.13253,https://github.com/OmkarThawakar/MSSTS-VIS,,, +Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer,Omkar Thawakar (MBZUAI)*; Sanath Narayan (Inception Institute of Artificial Intelligence); Jiale Cao (Tianjin University); Hisham Cholakkal (MBZUAI); Rao Muhammad Anwer (MBZUAI/AALTO); Muhammad Haris Khan (Muhammad Bin Zayed University of Artificial Intelligence); Salman Khan (MBZUAI/ANU); Michael Felsberg (Linköping University); Fahad Shahbaz Khan (MBZUAI),,,Poster,http://arxiv.org/abs/2203.13253,https://github.com/OmkarThawakar/MSSTS-VIS,,, RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation,"Haodi He (University of Science and Technology of China); Yuhui Yuan (Microsoft Research)*; Xiangyu Yue (University of California, Berkeley); Han Hu (Microsoft Research Asia)",,,Poster,http://arxiv.org/abs/2203.04187,,,, Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression,Ahmet Burakhan Koyuncu (Technical University of Munich)*; Han Gao (Tencent America); Atanas Boev (Huawei Technologies Duesseldorf GmbH); Georgii Gaikov (Huawei Moscow Research Center); Elena Alshina (Huawei Technologies); Eckehard Steinbach (TUM),,,Poster,http://arxiv.org/abs/2203.02452,,,, Image Super-Resolution with Deep Dictionary,Shunta Maeda (Navier Inc.)*,,,Poster,http://arxiv.org/abs/2207.09228,,,, ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement,"Dongli Tan (Xiamen University)*; Jiang-Jiang Liu (Nankai University); Xingyu Chen (Youtu Lab); Chao Chen (Youtu Laboratory); Ruixin Zhang (Tencent); Yunhang Shen (Xiamen University); Shouhong Ding (Tencent); Rongrong Ji (Xiamen University, China)",,,Poster,,,,, Responsive Listening Head Generation: A Benchmark Dataset and Baseline,Mohan Zhou (Harbin Institute of Technology)*; Yalong Bai (JD AI Research); Wei Zhang (JD AI Research); Ting Yao (JD AI Research); Tiejun Zhao (Harbin Institute of Technology); Tao Mei (AI Research of JD.com),,,Poster,http://arxiv.org/abs/2112.13548,,,, -WISE: Whitebox Image Stylization by Example-based Learning,"Winfried Lötzsch (Merantix Momentum); Max Reimann (Hasso-Plattner-Institute)*; Martin Büßemeyer (Hasso-Plattner-Institut); Amir Semmo (Digital Masterpieces GmbH); Jürgen Döllner (Hasso-Plattner-Institut); Matthias Trapp (Hasso Plattner Institute, University of Potsdam)",,,Poster,http://arxiv.org/abs/2207.14606,,,, +WISE: Whitebox Image Stylization by Example-based Learning,"Winfried Lötzsch (Merantix Momentum); Max Reimann (Hasso-Plattner-Institute)*; Martin Büßemeyer (Hasso-Plattner-Institut); Amir Semmo (Digital Masterpieces GmbH); Jürgen Döllner (Hasso-Plattner-Institut); Matthias Trapp (Hasso Plattner Institute, University of Potsdam)",,,Poster,http://arxiv.org/abs/2207.14606,,,, 3D Equivariant Graph Implicit Functions,"Yunlu Chen (University of Amsterdam)*; Basura Fernando (Agency for Science, Technology and Research, A*STAR, Singapore); Hakan Bilen (University of Edinburgh); Matthias Niessner (Technical University of Munich); Efstratios Gavves (University of Amsterdam )",,,Poster,http://arxiv.org/abs/2203.17178,,,, AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment,Kangyeol Kim (KAIST)*; Sunghyun Park (KAIST); Jaeseong Lee (KAIST); Sunghyo Chung (Korea University); Junsoo Lee (NAVER WEBTOON Ltd.); Jaegul Choo (Korea Advanced Institute of Science and Technology),,,Poster,http://arxiv.org/abs/2111.07640,https://github.com/kangyeolk/AnimeCeleb,,, "Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics",Sen Zhang (The University of Sydney); Jing Zhang (The University of Sydney)*; Dacheng Tao (The University of Sydney),,,Poster,http://arxiv.org/abs/2207.04680,,,, @@ -1335,7 +1333,7 @@ Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection, Learning Semantic Segmentation from Multiple Datasets with Label Shifts,Dongwan Kim (Seoul National University)*; Yi-Hsuan Tsai (Phiar Technologies); Yumin Suh (NEC Labs America); Masoud Faraki (NEC Labs); Sparsh Garg (NEC Labs America); Manmohan Chandraker (UC San Diego); Bohyung Han (Seoul National University),,,Poster,http://arxiv.org/abs/2202.14030,,,, SecretGen: Privacy Recovery on Pre-trained Models via Distribution Discrimination,Zhuowen Yuan (UIUC); Fan Wu (UIUC); Yunhui Long (University of Illinois); Chaowei Xiao (NVIDIA); Bo Li (UIUC)*,,,Poster,http://arxiv.org/abs/2207.12263,https://github.com/AI-secure/SecretGen,,, A Kendall Shape Space Approach to 3D Shape Estimation from 2D Landmarks,Martha Paskin (Zuse Institute Berlin); Daniel Baum (Zuse Institute Berlin); Mason N Dean (City University of Hong Kong); Christoph von Tycowicz (Zuse Institute Berlin)*,,,Poster,http://arxiv.org/abs/2207.12687,,,, -Temporally Consistent Transformer for Video Denoising,Mingyang Song (ETH Zurich)*; Yang Zhang (Disney Research Studios); Tunç Aydin (Disney Research),,,Poster,,,,, +Temporally Consistent Transformer for Video Denoising,Mingyang Song (ETH Zurich)*; Yang Zhang (Disney Research Studios); Tunç Aydin (Disney Research),,,Poster,,,,, Action Quality Assessment with Temporal Parsing Transformer,"Yang Bai (Durham University); Desen Zhou (Baidu, Inc.)*; Songyang Zhang (Shanghai AI Laboratory); Jian Wang (Baidu); Errui Ding (Baidu Inc.); Yu Guan (University of Warwick); Yang Long (Durham University); Jingdong Wang (Baidu)",,,Poster,http://arxiv.org/abs/2207.09270,,,, A study of Pre-training strategies and datasets for facial representation learning,"Adrian Bulat (Samsung AI Center, Cambridge)*; Shiyang Cheng (Samsung); Jing Yang (University of Nottingham); Andrew Garbett (Samsung AI Center); Enrique Sanchez (Samsung AI Centre); Georgios Tzimiropoulos (Queen Mary University of London)",,,Poster,,,,, Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images,Radu Alexandru Rosu (University of Bonn); Shunsuke Saito (Facebook); Ziyan Wang (Carnegie Mellon University); Chenglei Wu (Facebook Reality Labs); Sven Behnke (University of Bonn); Giljoo Nam (Facebook Inc.)*,,,Poster,http://arxiv.org/abs/2207.14067,,,, @@ -1345,13 +1343,13 @@ Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning,T GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs,Xin Liu (Tsinghua University)*; Xiaofei Shao (Deptrum); Bo Wang (Deptrum); Ya-Li Li (Tsinghua University); Shengjin Wang (Tsinghua University),,,Poster,,,,, Revisiting Batch Norm Initialization,Jim Davis (Ohio State University); Logan Frank (Ohio State University)*,,,Poster,http://arxiv.org/abs/2110.13989,https://github.com/osu-cvl/revisiting-bn-init,,, NewsStories: Illustrating articles with visual summaries,Reuben Tan (Boston University)*; Bryan Plummer (Boston University); Kate Saenko (Boston University); J.P. Lewis (Google Research); Avneesh Sud (Google); Thomas Leung (Google),,,Poster,http://arxiv.org/abs/2207.13061,,,, -Improving Few-Shot Learning through Multi-task Representation Learning Theory,"Quentin Bouniot (CEA, LIST)*; Ievgen Redko (Laboratoire Hubert Curien); Romaric Audigier (CEA LIST); Angélique Loesch (CEA LIST); Amaury Habrard (University of St-Etienne, Lab. H. Curien)",,,Poster,http://arxiv.org/abs/2010.01992,,,, +Improving Few-Shot Learning through Multi-task Representation Learning Theory,"Quentin Bouniot (CEA, LIST)*; Ievgen Redko (Laboratoire Hubert Curien); Romaric Audigier (CEA LIST); Angélique Loesch (CEA LIST); Amaury Habrard (University of St-Etienne, Lab. H. Curien)",,,Poster,http://arxiv.org/abs/2010.01992,,,, Deep Semantic Statistics Matching (D2SM) Denoising Network,"Kangfu Mei (Johns Hopkins University)*; Vishal Patel (Johns Hopkins University); Rui Huang (The Chinese University of Hong Kong, Shenzhen)",,,Poster,http://arxiv.org/abs/2207.09302,,,, Long-tailed Instance Segmentation using Gumbel Optimized Loss,Konstantinos P Alexandridis (University of Liverpool)*; Jiankang Deng (Imperial College London); Anh Nguyen (University of Liverpool); Shan Luo (University of Liverpool),,,Poster,http://arxiv.org/abs/2207.10936,https://github.com/kostas1515/GOL,,, DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection,"Jinhyung Park (Carnegie Mellon University)*; Chenfeng Xu (UC Berkeley); Yiyang Zhou (UC Berkeley ); Masayoshi TOMIZUKA (MSC Lab); Wei Zhan (University of California, Berkeley)",,,Poster,http://arxiv.org/abs/2203.09510,https://github.com/Divadi/DetMatch,,, 3D Scene Inference from Transient Histograms,"Sacha Jungerman (University of Wisconsin-Madison)*; Atul N Ingle (University of Wisconsin-Madison); Yin Li (University of Wisconsin-Madison); Mohit Gupta (""University of Wisconsin-Madison, USA "")",,,Poster,,,,, SSBNet: Improving Visual Recognition Efficiency by Adaptive Sampling,Ho Man Kwan (The Hong Kong University of Science and Technology)*; S.H. Song (HKUST),,,Poster,http://arxiv.org/abs/2207.11511,,,, -Deep 360° Optical Flow Estimation by Multi-Projection Fusion,Yiheng Li (Victoria University of Wellington); Connelly Barnes (Adobe); Kun Huang (Victoria University of Wellington); Fang-Lue Zhang (Victoria University of Wellington)*,,,Poster,,,,, +Deep 360° Optical Flow Estimation by Multi-Projection Fusion,Yiheng Li (Victoria University of Wellington); Connelly Barnes (Adobe); Kun Huang (Victoria University of Wellington); Fang-Lue Zhang (Victoria University of Wellington)*,,,Poster,,,,, Neural Space-filling Curves,Hanyu Wang (University of Maryland - College Park)*; Kamal Gupta (University of Maryland); Larry Davis (University of Maryland); Abhinav Shrivastava (University of Maryland),,,Poster,http://arxiv.org/abs/2204.08453,,,, MFIM: Megapixel Facial Identity Manipulation,Sanghyeon Na (kakaobrain)*,,,Poster,,,,, Objects Can Move: 3D Change Detection by GeometricTransformation Consistency,Aikaterini Adam (National Techniclal University of Athens)*; Torsten Sattler (Czech Technical University in Prague); Konstantinos Karantzalos (National Technical University of Athens); Tomas Pajdla (Czech Technical University in Prague),,,Poster,,,,, @@ -1359,13 +1357,13 @@ MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation,Bo Sun (UT Austin)*; Vladimir Kim (Adobe); Qixing Huang (The University of Texas at Austin); Noam Aigerman (Adobe); Siddhartha Chaudhuri (Adobe Research),,,Poster,http://arxiv.org/abs/2207.11790,https://github.com/GitBoSun/PatchRD,,, Network Binarization via Contrastive Learning,Yuzhang Shang (Illinois Institute of Technology)*; Dan Xu (The Hong Kong University of Science and Technology); Ziliang Zong (Texas State University); Liqiang Nie (Harbin Institute of Technology (Shenzhen)); Yan Yan (Illinois Institute of Technology),,,Poster,http://arxiv.org/abs/2207.02970,,,, Lipschitz Continuity Retained Binary Neural Network,Yuzhang Shang (Illinois Institute of Technology)*; Dan Xu (The Hong Kong University of Science and Technology); Bin Duan (Illinois Institute of Technology); Ziliang Zong (Texas State University); Liqiang Nie (Harbin Institute of Technology (Shenzhen)); Yan Yan (Illinois Institute of Technology),,,Poster,http://arxiv.org/abs/2207.06540,,,, -Is Geometry Enough for Matching in Visual Localization?,"Qunjie Zhou (Technical University of Munich)*; Sérgio Agostinho (Institute for Systems and Robotics, Instituto Superior Técnico, Universidade de Lisboa); Aljosa Osep (TUM Munich); Laura Leal-Taixé (TUM)",,,Poster,http://arxiv.org/abs/2203.12979,,,, +Is Geometry Enough for Matching in Visual Localization?,"Qunjie Zhou (Technical University of Munich)*; Sérgio Agostinho (Institute for Systems and Robotics, Instituto Superior Técnico, Universidade de Lisboa); Aljosa Osep (TUM Munich); Laura Leal-Taixé (TUM)",,,Poster,http://arxiv.org/abs/2203.12979,,,, Webly Supervised Concept Expansion for General Purpose Vision Models,Amita Kamath (Allen Institute for Artificial Intelligence); Christopher A Clark (Allen Institute for AI)*; Tanmay Gupta (Allen Institute for Artificial Intelligence); Eric Kolve (Allen AI); Derek Hoiem (University of Illinois at Urbana-Champaign); Aniruddha Kembhavi (Allen Institute for Artificial Intelligence),,,Poster,http://arxiv.org/abs/2202.02317,,,, Compositional Human-Scene Interaction Synthesis with Semantic Control,Kaifeng Zhao (ETH Zurich)*; Shaofei wang (ETH Zurich); Yan Zhang (ETH Zurich); Thabo Beeler (Disney Research | Studios); Siyu Tang (ETH Zurich),,,Poster,http://arxiv.org/abs/2207.12824,https://github.com/zkf1997/COINS,,, MaCLR: Motion-aware Contrastive Learning of Representations for Videos,Fanyi Xiao (Meta); Joseph Tighe (Amazon); Davide Modolo (Amazon)*,,,Poster,http://arxiv.org/abs/2106.09703,,,, Transformers as Meta-Learners for Implicit Neural Representations,Yinbo Chen (UC San Diego)*; Xiaolong Wang (UCSD),,,Poster,http://arxiv.org/abs/2208.02801,,,, RAWtoBit: A Fully End-to-end Camera ISP Network,Wooseok Jeong (Korea University); Seung-Won Jung (Korea University)*,,,Poster,http://arxiv.org/abs/2208.07639,,,, -SpatialDETR: Robust Scalable Transformer-Based 3D Object Detection from Multi-View Camera Images with Global Cross-Sensor Attention,Simon Doll (University of Tübingen)*; Richard Schulz (Mercedes Benz); Lukas Schneider (Daimer); Viviane Benzin (Mercedes-Benz AG); Markus Enzweiler (Esslingen University of Applied Sciences); Hendrik P. A. Lensch (University of Tübingen),,,Poster,,,,, +SpatialDETR: Robust Scalable Transformer-Based 3D Object Detection from Multi-View Camera Images with Global Cross-Sensor Attention,Simon Doll (University of Tübingen)*; Richard Schulz (Mercedes Benz); Lukas Schneider (Daimer); Viviane Benzin (Mercedes-Benz AG); Markus Enzweiler (Esslingen University of Applied Sciences); Hendrik P. A. Lensch (University of Tübingen),,,Poster,,,,, 3D Face Reconstruction with Dense Landmarks,Erroll Wood (Microsoft)*; Tadas Baltrusaitis (Microsoft); Charlie Hewitt (Microsoft); Matthew A Johnson (Microsoft); Jingjing Shen (Microsoft); Nikola Milosavljevic (Microsoft); Daniel S Wilde (Microsoft); Stephan J Garbin (University College London); Toby Sharp (Microsoft); Ivan Stojiljkovic (Microsoft); Tom Cashman (Microsoft); Julien Valentin (Microsoft),,,Poster,http://arxiv.org/abs/2204.02776,,,, SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds,Pei Sun (Waymo)*; Mingxing Tan (Waymo); Weiyue Wang (Waymo); Chenxi Liu (Waymo); Fei Xia (Waymo); Zhaoqi Leng (Waymo); Dragomir Anguelov (Waymo),,,Poster,,,,, Incomplete Multi-view Domain Adaptation via Channel Enhancement and Knowledge Transfer,Haifeng Xia (Tulane University)*; Pu Wang (MERL); Zhengming Ding (Tulane University),,,Poster,,,,, @@ -1412,12 +1410,12 @@ Weakly Supervised 3D Scene Segmentation with Region-Level Boundary Awareness and FOSTER: Feature Boosting and Compression for Class-Incremental Learning,Fu-Yun Wang (Nanjing University)*; Da-Wei Zhou (Nanjing University); Han-Jia Ye (Nanjing University); De-Chuan Zhan (Nanjing University),,,Poster,http://arxiv.org/abs/2204.04662,https://github.com/G-U-N/ECCV22-FOSTER,,, "Delving into Universal Lesion Segmentation: Method, Dataset, and Benchmark",Yu Qiu (Nankai University)*; Jing Xu (Nankai University),,,Poster,,,,, Explicit Model Size Control and Relaxation via Smooth Regularization for Mixed-Precision Quantization,"Vladimir Chikin (Huawei Noah's Ark Lab)*; Kirill Solodskikh (Huawei Noah's Ark Lab, MSU); Irina Zhelavskaya (Skolkovo Institute of Science and Technology (Skoltech))",,,Poster,,,,, -Large scale Real-world Multi Person Tracking,Bing Shuai (Amazon)*; Alessandro Bergamo (Amazon); Uta Büchler (Amazon); Andrew G Berneshawi (Amazon); Alyssa Boden (Amazon Web Services); Joseph Tighe (Amazon),,,Poster,,,,, +Large scale Real-world Multi Person Tracking,Bing Shuai (Amazon)*; Alessandro Bergamo (Amazon); Uta Büchler (Amazon); Andrew G Berneshawi (Amazon); Alyssa Boden (Amazon Web Services); Joseph Tighe (Amazon),,,Poster,,,,, Class-agnostic Object Detection with Multi-modal Transformer,Muhammad Maaz (MBZUAI)*; Hanoona Abdul Rasheed (MBZUAI); Salman Khan (MBZUAI/ANU); Fahad Shahbaz Khan (MBZUAI); Rao Muhammad Anwer (MBZUAI/AALTO); Ming-Hsuan Yang (University of California at Merced),,,Poster,http://arxiv.org/abs/2111.11430,,,, -Language-Grounded Indoor 3D Semantic Segmentation in the Wild,Dávid Rozenberszki (Technische Universitat Munchen)*; Or Litany (Stanford); Angela Dai (Technical University of Munich),,,Poster,http://arxiv.org/abs/2204.07761,,,, +Language-Grounded Indoor 3D Semantic Segmentation in the Wild,Dávid Rozenberszki (Technische Universitat Munchen)*; Or Litany (Stanford); Angela Dai (Technical University of Munich),,,Poster,http://arxiv.org/abs/2204.07761,,,, Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis,Jeong-gi Kwak (Korea University); Yuanming Li (Korea University); Dongsik Yoon (Korea University); Donghyeon Kim (Korea university); David K Han (Drexel University); Hanseok Ko (Korea University)*,,,Poster,http://arxiv.org/abs/2207.10257,https://github.com/jgkwak95/SURF-GAN,,, BASQ: Branch-wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks,Han-Byul Kim (Seoul National University)*; Eunhyeok Park (POSTECH); Sungjoo Yoo (Seoul National University),,,Poster,,,,, -AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields,Andreas Kurz (Graz University of Technology)*; Thomas Neff (Graz University of Technology); Zhaoyang Lv (Facebook); Michael Zollhöfer (Facebook Reality Labs); Markus Steinberger (Graz University of Technology),,,Poster,http://arxiv.org/abs/2207.10312,,,, +AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields,Andreas Kurz (Graz University of Technology)*; Thomas Neff (Graz University of Technology); Zhaoyang Lv (Facebook); Michael Zollhöfer (Facebook Reality Labs); Markus Steinberger (Graz University of Technology),,,Poster,http://arxiv.org/abs/2207.10312,,,, Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertion,"Zian Wang (University of Toronto)*; Wenzheng Chen (University of Toronto); David Acuna (University of Toronto, NVIDIA); Jan Kautz (NVIDIA); Sanja Fidler (University of Toronto, NVIDIA)",,,Poster,http://arxiv.org/abs/2208.09480,,,, Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation,Min Zhang (Zhejiang University)*; Siteng Huang (Westlake University); Wenbin Li (Nanjing University); Donglin Wang (Westlake University),,,Poster,http://arxiv.org/abs/2207.06989,https://github.com/remiMZ/HTS-ECCV22,,, PoseScript: 3D Human Poses from Natural Language,Ginger Delmas (NAVER LABS EUROPE)*; Philippe Weinzaepfel (NAVER LABS Europe); Thomas LUCAS (Naver); Francesc Moreno (IRI); Gregory Rogez (NAVER LABS Europe),,,Poster,,,,, @@ -1456,25 +1454,25 @@ Recover Fair Deep Classification Models via Altering Pre-trained Structure,Yanfu Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism,Yangyang Shu (University of Adelaide); Lingqiao Liu (University of Adelaide)*; Baosheng Yu (The University of Sydney); Haiming Xu (The University of Adelaide),,,Poster,http://arxiv.org/abs/2208.00617,https://github.com/GANPerf/SAM,,, VSA: Learning Varied-Size Window Attention in Vision Transformers,Qiming Zhang (The University of Sydney)*; YUFEI XU (University of sydney); Jing Zhang (The University of Sydney); Dacheng Tao (JD.com),,,Poster,http://arxiv.org/abs/2204.08446,https://github.com/ViTAE-Transformer/ViTAE-VSA,,, PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting,Thomas LUCAS (Naver)*; Fabien Baradel (Naver Labs Europe); Philippe Weinzaepfel (NAVER LABS Europe); Gregory Rogez (NAVER LABS Europe),,,Poster,,,,, -CAViT: Contextual Alignment Vision Transformer for Video Object Re-identification,"jinlin wu (Institute of Automation, Chinese Academy of Sciences, Beijing, China)*; He Lingxiao (nlpr，cripac); Wu Liu (AI Research of JD.com); Yang Yang (Institute of Automation, Chinese Academy of Sciences); Zhen Lei (NLPR, CASIA, China); Tao Mei (AI Research of JD.com); Stan Z. Li (Westlake University)",,,Poster,,,,, +CAViT: Contextual Alignment Vision Transformer for Video Object Re-identification,"jinlin wu (Institute of Automation, Chinese Academy of Sciences, Beijing, China)*; He Lingxiao (nlpr，cripac); Wu Liu (AI Research of JD.com); Yang Yang (Institute of Automation, Chinese Academy of Sciences); Zhen Lei (NLPR, CASIA, China); Tao Mei (AI Research of JD.com); Stan Z. Li (Westlake University)",,,Poster,,,,, Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution,Cheng Ma (Tsinghua University); Jingyi Zhang (Tsinghua University); Jie Zhou (Tsinghua University); Jiwen Lu (Tsinghua University)*,,,Poster,http://arxiv.org/abs/2207.12987,https://github.com/zhjy2016/SPLUT,,, Frozen CLIP Models are Efficient Video Learners,"Ziyi Lin (The Chinese University of Hong Kong)*; Shijie Geng (Rutgers University); Renrui Zhang (Shanghai AI Lab); Peng Gao (Chinese university of hong kong); Gerard de Melo (Hasso Plattner Institute); Xiaogang Wang (Chinese University of Hong Kong, Hong Kong); Jifeng Dai (SenseTime); Yu Qiao (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences); Hongsheng Li (The Chinese University of Hong Kong)",,,Poster,http://arxiv.org/abs/2208.03550,https://github.com/OpenGVLab/efficient-video-recognition,,, Deforming Radiance Fields with Cages,Tianhan Xu (The University of Tokyo)*; Tatsuya Harada (The University of Tokyo / RIKEN),,,Poster,http://arxiv.org/abs/2207.12298,,,, GeoAug: Data Augmentation for Few-Shot NeRF with Geometry Constrains,Di Chen (Alibaba Group)*; Yu Liu (Alibaba Group); Lianghua Huang (Alibaba Group); bin wang (alibaba group); Pan Pan (Alibaba Group),,,Poster,,,,, -DoodleFormer: Creative Sketch Drawing with Transformers,Ankan Kumar Bhunia (MBZUAI)*; Salman Khan (MBZUAI/ANU); Hisham Cholakkal (MBZUAI); Rao Muhammad Anwer (MBZUAI/AALTO); Fahad Shahbaz Khan (MBZUAI); Jorma Laaksonen (Aalto University); Michael Felsberg (Linköping University),,,Poster,http://arxiv.org/abs/2112.03258,,,, +DoodleFormer: Creative Sketch Drawing with Transformers,Ankan Kumar Bhunia (MBZUAI)*; Salman Khan (MBZUAI/ANU); Hisham Cholakkal (MBZUAI); Rao Muhammad Anwer (MBZUAI/AALTO); Fahad Shahbaz Khan (MBZUAI); Jorma Laaksonen (Aalto University); Michael Felsberg (Linköping University),,,Poster,http://arxiv.org/abs/2112.03258,,,, Implicit Neural Representations for Variable Length Human Motion Generation,Pablo Alberto Cervantes Baque (Tokyo Institute of Technology)*; Yusuke Sekikawa (Denso IT Laboratory); Ikuro Sato (Tokyo Institute of Technology / Denso IT Laboratory); Koichi SHINODA (Tokyo Institute of Technology),,,Poster,http://arxiv.org/abs/2203.13694,https://github.com/PACerv/ImplicitMotion,,, FLEX: Extrinsic Parameters-free Multi-view 3D Human Motion Reconstruction,Brian Gordon (Tel Aviv University); Sigal Raab (Tel Aviv University)*; Guy Azov (Tel Aviv University); Raja Giryes (Tel Aviv University); Danny Cohen-Or (Tel Aviv University),,,Poster,,,,, Pairwise Contrastive Learning Network for Action Quality Assessment,Mingzhe Li (Huaqiao University); Hong-Bo Zhang (Huaqiao University)*; Qing Lei (Huaqiao University); Zongwen Fan (Huaqiao University); Jinghua Liu (Huaqiao University); Ji-Xiang Du (Huaqiao University),,,Poster,,,,, Large-displacement 3D Object Tracking with Hybrid Non-local Optimization,Xuhui Tian (Shandong University)*; Xinran Lin (Shandong University); Fan Zhong (Shandong University); Xueying N/A Qin (Shandong University),,,Poster,http://arxiv.org/abs/2207.12620,https://github.com/cvbubbles/nonlocal-3dtracking,,, Learning Object Placement via Dual-path Graph Completion,Siyuan Zhou (Shanghai Jiao Tong University)*; Liu Liu (Shanghai Jiao Tong University); Li Niu (Shanghai Jiao Tong University); Liqing Zhang (Shanghai Jiao Tong University),,,Poster,http://arxiv.org/abs/2207.11464,,,, Unbiased Manifold Augmentation for Coarse Class Subdivision,Baoming Yan (Alibaba Group)*; KE GAO (alibaba-inc); Bo Gao (Alibaba Group); Lin Wang (Alibaba-inc); Jiang Yang (Alibaba Group); Xiaobo Li (Alibaba),,,Poster,,,,, -Rethinking Video Rain Streak Removal: A New Synthesis Model and A Deraining Network with Video Rain Prior,"Shuai Wang ( College of Intelligence and Computing, Tianjin University); Lei Zhu (The Hong Kong University of Science and Technology (Guangzhou))*; Huazhu Fu (IHPC, ASTAR); Jing Qin (The Hong Kong Polytechnic University); Carola-Bibiane B Schönlieb (Cambridge University); Wei Feng (School of Computer Science and Technology, Tianjin University); Song Wang (University of South Carolina)",,,Poster,,,,, +Rethinking Video Rain Streak Removal: A New Synthesis Model and A Deraining Network with Video Rain Prior,"Shuai Wang ( College of Intelligence and Computing, Tianjin University); Lei Zhu (The Hong Kong University of Science and Technology (Guangzhou))*; Huazhu Fu (IHPC, ASTAR); Jing Qin (The Hong Kong Polytechnic University); Carola-Bibiane B Schönlieb (Cambridge University); Wei Feng (School of Computer Science and Technology, Tianjin University); Song Wang (University of South Carolina)",,,Poster,,,,, Expanded Adaptive Scaling Normalization for End to End Image Compression,Chajin Shin (Yonsei University)*; Hyeongmin Lee (Yonsei University ); Hanbin Son (Yonsei Univ.); Sangjin Lee (Yonsei University); Dogyoon Lee (Yonsei University); Sangyoun Lee (Yonsei University),,,Poster,http://arxiv.org/abs/2208.03049,,,, Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets,Paul Albert (Insight Centre for Data Analytics (DCU))*; Eric Arazo (Insight Centre for Data Analytics (DCU)); Noel O Connor (Home); Kevin McGuinness (DCU),,,Poster,http://arxiv.org/abs/2207.01573,,,, Filter Pruning via Feature Discrimination in Deep Neural Networks,"Zhiqiang He (Zhejiang University of Science and Technology)*; Yaguan QIAN (Zhejiang University of Science and Technology); Yuqi Wang (Zhejiang University of Science and Technology); Bin WANG (Network and Information Security Laboratory of Hangzhou Hikvision Digital Technology Co.); Xiaohui Guan (Zhejiang University of Water Resources and Electric Power); Zhaoquan Gu (Guangzhou University); Xiang Ling (Institute of Software, Chinese Academy of Sciences); Shaoning Zeng (Yangtze Delta Region Institute (Huzhou), University of Electronic Science and Technology of China); Haijiang Wang (Zhejiang University of Science and Technology); Wujie Zhou (Zhejiang University of Science and Technology)",,,Poster,,,,, VoViT: Low Latency Graph-based Audio-Visual Voice Separation Transformer,Juan Felipe Montesinos (Universitat Pompeu Fabra)*; Venkatesh Shenoy Kadandale (Universitat Pompeu Fabra); Gloria Haro (Universitat Pompeu Fabra),,,Poster,http://arxiv.org/abs/2203.04099,,,, SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition,"Dajian Zhong (East China Normal University)*; Shujing Lv (East China Normal University); Palaiahnakote Shivakumara (University of Malaya); Bing Yin (IFLYTEK Co.,Ltd); Jiajia Wu (IFLYTEK Co.,Ltd); Umapada Pal (Indian Statistical Institute, Kolkata); Yue Lu (East China Normal University)",,,Poster,http://arxiv.org/abs/2207.10256,,,, -DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition,"Matej Grcić (University of Zagreb, Faculty of Electrical Engineering and Computing)*; Petra Bevandić (Faculty of Electrical Engineering and Computing); Sinisa Segvic (UniZg-FER)",,,Poster,http://arxiv.org/abs/2207.02606,,,, +DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition,"Matej Grcić (University of Zagreb, Faculty of Electrical Engineering and Computing)*; Petra Bevandić (Faculty of Electrical Engineering and Computing); Sinisa Segvic (UniZg-FER)",,,Poster,http://arxiv.org/abs/2207.02606,,,, D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights,"Yuzhen Zhang (Zhengzhou University); Wentong Wang (Zhengzhou University); weizhi guo (zhengzhou university); Pei Lv (Zhengzhou University)*; Mingliang Xu (Zhengzhou University); Wei Chen (State Key Lab of CAD&CG, Zhejiang University); Dinesh Manocha (University of Maryland at College Park)",,,Poster,,,,, Where in the World is this Image? Transformer-based Geo-localization in the Wild,Shraman Pramanick (Johns Hopkins University)*; Ewa M Nowara (Meta Reality Labs); Joshua Gleason (Univ of Maryland); Carlos Castillo (Johns Hopkins University); Rama Chellappa (Johns Hopkins University),,,Poster,http://arxiv.org/abs/2204.13861,,,, MODE: Multi-view Omnidirectional Depth Estimation with 360-degree Cameras,Ming Li (NanJing University)*; Xueqian Jin (Nanjing University); Xuejiao Hu (Nanjing University); Jingzhao Dai (Nanjing University); Sidan Du (Nanjing University); Yang Li (NanJing University),,,Poster,,,,, @@ -1485,12 +1483,12 @@ PIP: Physical Interaction Prediction via Mental Simulation with Span Selection," Generator Knows What Discriminator Should Learn in Unconditional GANs,"Gayoung Lee (NAVER AI Lab)*; Hyunsu Kim (NAVER AI Lab); Junho Kim (NAVER AI Lab); Seonghyeon Kim (Clova AI Research, NAVER Corp.); Jung-Woo Ha (NAVER CLOVA AI Lab); Yunjey Choi (NAVER AI Lab)",,,Poster,http://arxiv.org/abs/2207.13320,https://github.com/naver-ai/GGDR,,, A Gyrovector Space Approach for Symmetric Positive Semi-definite Matrix Learning,Xuan Son Nguyen (Ensea)*,,,Poster,,,,, Compositional Visual Generation with Composable Diffusion Models,Nan Liu (University of Illinois at Urbana-Champaign); Shuang Li (MIT); Yilun Du (MIT)*; Antonio Torralba (MIT); Joshua Tenenbaum (MIT),,,Poster,http://arxiv.org/abs/2206.01714,,,, -Temporal and cross-modal attention for audio-visual zero-shot learning,Otniel-Bogdan Mercea (University of Tübingen)*; Thomas Hummel (University of Tübingen); A. Sophia Koepke (University of Tübingen); Zeynep Akata (University of Tübingen),,,Poster,http://arxiv.org/abs/2207.09966,https://github.com/ExplainableML/TCAF-GZSL,,, +Temporal and cross-modal attention for audio-visual zero-shot learning,Otniel-Bogdan Mercea (University of Tübingen)*; Thomas Hummel (University of Tübingen); A. Sophia Koepke (University of Tübingen); Zeynep Akata (University of Tübingen),,,Poster,http://arxiv.org/abs/2207.09966,https://github.com/ExplainableML/TCAF-GZSL,,, Telepresence Video Quality Assessment,Zhenqiang Ying (The University of Texas at Austin)*; Deepti Ghadiyaram (Facebook); Alan Bovik (University of Texas at Austin),,,Poster,http://arxiv.org/abs/2207.09956,,,, Enhancing Multi-modal Features Using Local Self-attention for 3D Object Detection,"hao li (Hikvision Digital Technology Co. Ltd)*; Zehan Zhang (Shanghai Jiao Tong University & Hangzhou Hikvision Digital Technology Co. Ltd); Zhao Xian (Hikvision); yulong wang (Hikvision Digital Technology Co. Ltd); Yuxi Shen (Hikvision); Shiliang Pu (Hikvision Research Institute); Hui Mao (Hangzhou hikvision digital technology Co.,Ltd)",,,Poster,,,,, Totems: Physical Objects for Verifying Visual Integrity,Jingwei Ma (University of Washington)*; Lucy Chai (MIT); Minyoung Huh (MIT); Tongzhou Wang (MIT); Ser-Nam Lim (Meta AI); Phillip Isola (MIT); Antonio Torralba (MIT),,,Poster,,,,, -ManiFest: manifold deformation for few-shot image translation,Fabio Pizzati (Inria / Vislab)*; Jean-Francois Lalonde (Université Laval); Raoul de Charette (Inria),,,Poster,http://arxiv.org/abs/2111.13681,https://github.com/cv-rits/Manifest,,, -3D Shape Sequence of Human Comparison and Classification using Current and Varifolds,Emery Pierson (Université de Lille)*; Mohamed Daoudi (IMT Lille Douai); Sylvain Arguillere (Institute Camille Jordan),,,Poster,http://arxiv.org/abs/2207.12485,https://github.com/CRISTAL-3DSAM/HumanComparisonVarifolds,,, +ManiFest: manifold deformation for few-shot image translation,Fabio Pizzati (Inria / Vislab)*; Jean-Francois Lalonde (Université Laval); Raoul de Charette (Inria),,,Poster,http://arxiv.org/abs/2111.13681,https://github.com/cv-rits/Manifest,,, +3D Shape Sequence of Human Comparison and Classification using Current and Varifolds,Emery Pierson (Université de Lille)*; Mohamed Daoudi (IMT Lille Douai); Sylvain Arguillere (Institute Camille Jordan),,,Poster,http://arxiv.org/abs/2207.12485,https://github.com/CRISTAL-3DSAM/HumanComparisonVarifolds,,, Decouple-and-Sample: Protecting sensitive information in task agnostic data release,Abhishek Singh (MIT)*; Ethan Garza (MIT); Ayush Chopra (MIT); Praneeth Vepakomma (MIT); Vivek Sharma (MIT); Ramesh Raskar (Massachusetts Institute of Technology),,,Poster,,,,, Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space,"Wenqi Shao (The Chinese University of HongKong)*; Xun Zhao (Tencent Company); Yixiao Ge (Tencent); Zhaoyang Zhang (The Chinese University of Hong Kong); Lei Yang (Tencent); Xiaogang Wang (Chinese University of Hong Kong, Hong Kong); Ying Shan (Tencent); Ping Luo (The University of Hong Kong)",,,Poster,http://arxiv.org/abs/2207.03036,https://github.com/TencentARC/SFDA,,, Object Detection as Probabilistic Set Prediction,Georg Hess (Chalmers University of Technology)*; Christoffer Petersson (Zenseact); Lennart Svensson (Chalmers University of Technology),,,Poster,http://arxiv.org/abs/2203.07980,https://github.com/georghess/pmb-nll,,, @@ -1499,7 +1497,7 @@ Uncertainty-guided Source-free Domain Adaptation,"Subhankar Roy (University of T LA3: Efficient Label-Aware AutoAugment,Mingjun Zhao (University of Alberta)*; Shan Lu (University of Alberta); Zixuan Wang (Tencent Inc.); Xiaoli Wang (Tencent); Di Niu (University of Alberta),,,Poster,,,,, Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions,"Zhi Li (University of California, Berkeley)*; Lu He (Tencent America); Huijuan Xu (Pennsylvania State University)",,,Poster,http://arxiv.org/abs/2207.11805,,,, Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos,Tanqiu Qiao (Durham University); Qianhui Men (University of Oxford); Frederick W. B. Li (University of Durham); Yoshiki Kubotani (Waseda University); Shigeo Morishima (Waseda Research Institute for Science and Engineering); Hubert P. H. Shum (Durham University)*,,,Poster,http://arxiv.org/abs/2207.09425,,,, -"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker",Vasyl Borsuk (Ukrainian Catholic University); Roman Vei (Ukrainian Catholic University); Orest Kupyn (Ukrainian Catholic University); Tetiana Martyniuk (Ukrainian Catholic University)*; Igor Krashenyi (Piñata Farms); Jiri Matas (CMP CTU FEE),,,Poster,http://arxiv.org/abs/2112.07957,https://github.com/PinataFarms/FEARTracker,,, +"FEAR: Fast, Efficient, Accurate and Robust Visual Tracker",Vasyl Borsuk (Ukrainian Catholic University); Roman Vei (Ukrainian Catholic University); Orest Kupyn (Ukrainian Catholic University); Tetiana Martyniuk (Ukrainian Catholic University)*; Igor Krashenyi (Piñata Farms); Jiri Matas (CMP CTU FEE),,,Poster,http://arxiv.org/abs/2112.07957,https://github.com/PinataFarms/FEARTracker,,, Variance-Aware Weight Initializationfor Point Convolutional Neural Networks,Pedro Hermosilla Casajus (Ulm University)*; Michael Schelling (Ulm University - Institute of Media Informatics); Tobias Ritschel (UCL); Timo Ropinski (Ulm University),,,Poster,,,,, Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training,Haoxuan You (Columbia University)*; Luowei Zhou (Microsoft); Bin Xiao (Microsoft); Noel C Codella (Microsoft); Yu Cheng (Microsoft Research); Ruochen Xu (Microsoft); Shih-Fu Chang (Columbia University); Lu Yuan (Microsoft),,,Poster,http://arxiv.org/abs/2207.12661,https://github.com/Hxyou/MSCLIP,,, Single-Stream Multi-Level Alignment for Vision-Language Pretraining,Zaid Khan (Northeastern University)*; Vijay Kumar B G (NEC Laboratories America); Xiang Yu (NEC Labs); Samuel Schulter (NEC Laboratories America); Manmohan Chandraker (UC San Diego); YUN FU (Northeastern University),,,Poster,http://arxiv.org/abs/2203.14395,,,, @@ -1518,7 +1516,7 @@ How stable are Transferability Metrics evaluations?,Andrea Agostinelli (Google)* A Comparative Study of Graph Matching Algorithms in Computer Vision,"Stefan Haller (Heidelberg University)*; Lorenz Feineis (Heidelberg University); Lisa Hutschenreiter (Heidelberg University); Florian Bernard (University of Bonn); Carsten Rother (University of Heidelberg); Dagmar Kainmueller (MDC); Paul Swoboda (MPI fuer Informatik, Saarbruecken); Bogdan Savchynskyy (Heidelberg University)",,,Poster,http://arxiv.org/abs/2207.00291,,,, HM: Hybrid Masking for Few-Shot Segmentation,Seonghyeon Moon (Rutgers University)*; Samuel S Sohn (Rutgers University); Honglu Zhou (Rutgers University); Sejong Yoon (The College of New Jersey); Vladimir Pavlovic (Rutgers University); Muhammad Haris Khan (Muhammad Bin Zayed University of Artificial Intelligence); Mubbasir Kapadia (Rutgers),,,Poster,http://arxiv.org/abs/2203.12826,https://github.com/moonsh/HM-Hybrid-Masking,,, UCTNet: Uncertainty-aware Cross-modal Transformer Network for Indoor RGB-D Semantic Segmentation,Xiaowen Ying (Lehigh University)*; Mooi Choo Chuah (Lehigh University),,,Poster,,,,, -Learning Omnidirectional Flow in 360° Video via Siamese Representation,Keshav Bhandari (Texas State University)*; Bin Duan (Illinois Institute of Technology); Gaowen Liu (Cisco Research); Hugo M Latapie (Cisco); Ziliang Zong (Texas State University); Yan Yan (Illinois Institute of Technology),,,Poster,,,,, +Learning Omnidirectional Flow in 360° Video via Siamese Representation,Keshav Bhandari (Texas State University)*; Bin Duan (Illinois Institute of Technology); Gaowen Liu (Cisco Research); Hugo M Latapie (Cisco); Ziliang Zong (Texas State University); Yan Yan (Illinois Institute of Technology),,,Poster,,,,, Improving Generalization in Federated Learning by Seeking Flat Minima,Debora Caldarola (Politecnico di Torino)*; Barbara Caputo (Politecnico di Torino); Marco Ciccone (Politecnico di Torino),,,Poster,http://arxiv.org/abs/2203.11834,,,, Efficient Deep Visual and Inertial Odometry with Adaptive Visual Modality Selection,Mingyu Yang (University of Michigan)*; Yu Chen (University of Michigan); Hun Seok Kim (Nil),,,Poster,http://arxiv.org/abs/2205.06187,https://github.com/mingyuyng/Visual-Selective-VIO,,, MultiMAE: Multi-modal Multi-task Masked Autoencoders,Roman Bachmann (EPFL)*; David Mizrahi (EPFL); Andrei Atanov (EPFL); Amir Zamir (Swiss Federal Institute of Technology (EPFL)),,,Poster,http://arxiv.org/abs/2204.01678,,,, @@ -1536,7 +1534,7 @@ Panoramic Vision Transformer for Saliency Detection in 360 Videos,Heeseung Yun ( ActiveNeRF: Learning where to See with Uncertainty Estimation,"Xuran Pan (Tsinghua University); Zihang Lai (CMU); Shiji Song (Department of Automation, Tsinghua University); Gao Huang (Tsinghua)*",,,Poster,,,,, incDFM: Incremental Deep Feature Modeling for Continual Novelty Detection,Amanda S Rios (University of Southern California; Intel )*; Nilesh A Ahuja (Intel); Ibrahima Ndiour (Intel); Ergin U Genc (Intel); Laurent Itti (University of Southern California); Omesh Tickoo (Intel),,,Poster,,,,, BA-Net: Bridge Attention for Deep Convolutional Neural Networks,Yue Zhao (Sun Yat-sen University); Junzhou Chen (Sun Yat-sen University)*; Zhang Zirui (Sun Yat-sen University); Ronghui Zhang (Sun Yat-Sen University),,,Poster,,,,, -Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images,"Jinjin Gu (The University of Sydney)*; Haoming CAI (University of Maryland, College Park); Chenyu Dong (Graduate school at Shenzhen , Tsinghua University); Ruofan Zhang (Tsinghua University); Yulun Zhang (ETH Zurich); Wenming Yang (Tsinghua University); Chun Yuan (Graduate school at ShenZhen，Tsinghua university)",,,Poster,,,,, +Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images,"Jinjin Gu (The University of Sydney)*; Haoming CAI (University of Maryland, College Park); Chenyu Dong (Graduate school at Shenzhen , Tsinghua University); Ruofan Zhang (Tsinghua University); Yulun Zhang (ETH Zurich); Wenming Yang (Tsinghua University); Chun Yuan (Graduate school at ShenZhen，Tsinghua university)",,,Poster,,,,, Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance,Zhihang Zhong (The University of Tokyo); Xiao Sun (Microsoft Research Asia); Zhirong Wu (Microsoft Research); Yinqiang Zheng (The University of Tokyo); Stephen Lin (Microsoft Research)*; Imari Sato (National Institute of Informatics),,,Poster,http://arxiv.org/abs/2207.10123,https://github.com/zzh-tech/Animation-from-Blur,,, Zero-Shot Attribute Attacks on Fine-Grained Recognition Models,Nasim Shafiee (Northeastern University)*; Ehsan Elhamifar (Northeastern University),,,Poster,,,,, Break and Make: Interactive Structural Understanding Using LEGO Bricks,"Aaron T Walsman (University of Washington)*; Muru Zhang (University of Washington); Klemen Kotar (Allen Institute for AI); Karthik Desingh (University Washington); Dieter Fox (NVIDIA Research / University of Washington); Ali Farhadi (University of Washington, Allen Institue for AI, Apple)",,,Poster,http://arxiv.org/abs/2207.13738,,,, @@ -1565,8 +1563,8 @@ IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Rec LANA: Latency Aware Network Acceleration,Pavlo Molchanov (NVIDIA)*; James B Hall (Microsoft Research); Hongxu Yin (NVIDIA ); Nicolo Fusi (Microsoft Research); Jan Kautz (NVIDIA); Arash Vahdat (NVIDIA),,,Poster,http://arxiv.org/abs/2107.10624,,,, A Sketch Is Worth a Thousand Words:Image Retrieval with Text and Sketch,"Patsorn Sangkloy (Georgia Institute of Technology)*; Wittawat Jitkrittum (Google Research); Diyi Yang (Georgia Institute of Technology); James Hays (Georgia Institute of Technology, USA)",,,Poster,,,,, "HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking",Haoxian Zhang (Tencent)*; Yonggen Ling (Tencent),,,Poster,,,,, -3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization,"Rui Qiu (Xi’an Jiaotong-Liverpool University, University of Liverpool); Ming Xu (Xi'an Jiaotong-Liverpool University)*; Yuyao Yan (Xi'an Jiaotong-Liverpool University); Jeremy S Smith (University of Liverpool); Xi Yang (Xi’an Jiaotong Liverpool University )",,,Poster,http://arxiv.org/abs/2207.10895,,,, -Masked Siamese Networks for Label-Efficient Learning,Mahmoud Assran (Facebook AI)*; Mathilde Caron (Facebook Artificial Intelligence Research); Ishan Misra (Facebook AI Research); Piotr Bojanowski (Facebook); Florian Bordes (MILA); Pascal Vincent (Facebook FAIR & MILA Université de Montréal); Armand Joulin (Facebook AI Research); Mike Rabbat (Facebook FAIR); Nicolas Ballas (Facebook FAIR),,,Poster,http://arxiv.org/abs/2204.07141,,,, +3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization,"Rui Qiu (Xi’an Jiaotong-Liverpool University, University of Liverpool); Ming Xu (Xi'an Jiaotong-Liverpool University)*; Yuyao Yan (Xi'an Jiaotong-Liverpool University); Jeremy S Smith (University of Liverpool); Xi Yang (Xi’an Jiaotong Liverpool University )",,,Poster,http://arxiv.org/abs/2207.10895,,,, +Masked Siamese Networks for Label-Efficient Learning,Mahmoud Assran (Facebook AI)*; Mathilde Caron (Facebook Artificial Intelligence Research); Ishan Misra (Facebook AI Research); Piotr Bojanowski (Facebook); Florian Bordes (MILA); Pascal Vincent (Facebook FAIR & MILA Université de Montréal); Armand Joulin (Facebook AI Research); Mike Rabbat (Facebook FAIR); Nicolas Ballas (Facebook FAIR),,,Poster,http://arxiv.org/abs/2204.07141,,,, A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation,Wuyang Chen (University of Texas at Austin)*; Xianzhi Du (Google Brain); Fan Yang (Google); Lucas Beyer (Google Brain); Xiaohua Zhai (Google Brain); Tsung-Yi Lin (Google Brain); Huizhong Chen (Google); Jing Li (Google Brain); Xiaodan Song (Google Brain); Zhangyang Wang (University of Texas at Austin); Denny Zhou (Google Brain),,,Poster,,,,, A Cloud 3D Dataset and Application-Specific Learned Image Compression in Cloud 3D,Tianyi Liu (The University of Texas at San Antonio)*; Sen He (The University of Texas at San Antonio); Vinodh Kumaran Jayakumar (UTSA); Wei Wang (The University of Texas at San Antonio),,,Poster,,,,, Cross-Domain Few-Shot Semantic Segmentation,"Shuo Lei (Virginia Tech)*; Xuchao Zhang (NEC Labs America); Jianfeng He (Virginia Tech); Fanglan Chen (Virginia Tech); Bowen Du (Beihang Univeristy); Chang-Tien Lu (Virginia Tech, USA)",,,Poster,,,,, @@ -1574,17 +1572,17 @@ VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairmen Towards Metrical Reconstruction of Human Faces,Wojciech Zielonka (Max Planck Institute for Intelligent Systems); Timo Bolkart (Max Planck Institute for Intelligent Systems); Justus Thies (Max Planck Institute for Intelligent Systems)*,,,Poster,http://arxiv.org/abs/2204.06607,,,, DeepShadow: Neural Shape from Shadow,Asaf Karnieli (Reichman University)*; Yacov Hel-Or (The Interdisciplinary Center); Ohad Fried (IDC Herzliya),,,Poster,http://arxiv.org/abs/2203.15065,,,, Class-Incremental Learning with Cross-Space Clustering and Controlled Transfer,"Arjun Ashok (Indian Institute of Technology, Hyderabad)*; Joseph K J (Indian Institute of Technology, Hyderabad); Vineeth N Balasubramanian (Indian Institute of Technology, Hyderabad)",,,Poster,http://arxiv.org/abs/2208.03767,,,, -Object discovery and representation networks,Olivier Henaff (DeepMind)*; Skanda Koppula (DeepMind); Evan Shelhamer (DeepMind); Daniel Zoran (DeepMind); Andrew Jaegle (DeepMind); Andrew Zisserman (Oxford University); Joao Carreira (DeepMind); Relja Arandjelović (DeepMind),,,Poster,http://arxiv.org/abs/2203.08777,,,, +Object discovery and representation networks,Olivier Henaff (DeepMind)*; Skanda Koppula (DeepMind); Evan Shelhamer (DeepMind); Daniel Zoran (DeepMind); Andrew Jaegle (DeepMind); Andrew Zisserman (Oxford University); Joao Carreira (DeepMind); Relja Arandjelović (DeepMind),,,Poster,http://arxiv.org/abs/2203.08777,,,, MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks,"Benoit Guillard (EPFL)*; Federico Stella (EPFL); Pascal Fua (EPFL, Switzerland)",,,Poster,http://arxiv.org/abs/2111.14549,,,, -Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization,"Hannah M Schlueter (Imperial College London)*; Jeremy Tan (Imperial College London); Benjamin Hou (Imperial College London); Bernhard Kainz (Imperial College London, FAU Erlangen-Nürnberg)",,,Poster,http://arxiv.org/abs/2109.15222,https://github.com/hmsch/natural-synthetic-anomalies,,, +Natural Synthetic Anomalies for Self-Supervised Anomaly Detection and Localization,"Hannah M Schlueter (Imperial College London)*; Jeremy Tan (Imperial College London); Benjamin Hou (Imperial College London); Bernhard Kainz (Imperial College London, FAU Erlangen-Nürnberg)",,,Poster,http://arxiv.org/abs/2109.15222,https://github.com/hmsch/natural-synthetic-anomalies,,, Shap-CAM: Visual Explanations for Convolutional Neural Networks based on Shapley Value,Quan Zheng (Tsinghua University); Ziwei Wang (Tsinghua University); Jie Zhou (Tsinghua University); Jiwen Lu (Tsinghua University)*,,,Poster,,,,, -Simple Open-Vocabulary Object Detection with Vision Transformers,Matthias Minderer (Google Research)*; Alexey Gritsenko (Google Brain); Austin C Stone (Google); Maxim Neumann (Google); Dirk Weißenborn (German Research Center for Artificial Intelligence); Alexey Dosovitskiy (Inceptive); Aravindh Mahendran (Google); Anurag Arnab (Google); Mostafa Dehghani (Google Brain); Zhuoran Shen (Pony.ai); Xiao Wang (Google); Xiaohua Zhai (Google Brain); Thomas Kipf (Google Brain); Neil Houlsby (Google),,,Poster,http://arxiv.org/abs/2205.06230,,,, +Simple Open-Vocabulary Object Detection with Vision Transformers,Matthias Minderer (Google Research)*; Alexey Gritsenko (Google Brain); Austin C Stone (Google); Maxim Neumann (Google); Dirk Weißenborn (German Research Center for Artificial Intelligence); Alexey Dosovitskiy (Inceptive); Aravindh Mahendran (Google); Anurag Arnab (Google); Mostafa Dehghani (Google Brain); Zhuoran Shen (Pony.ai); Xiao Wang (Google); Xiaohua Zhai (Google Brain); Thomas Kipf (Google Brain); Neil Houlsby (Google),,,Poster,http://arxiv.org/abs/2205.06230,,,, Video Restoration Framework and its Meta-adaptations to Data-poor Conditions,"Prashant W Patil (Deakin University)*; Sunil Gupta (Deakin University, Australia); Santu Rana (Deakin University, Australia); Svetha Venkatesh (Deakin University)",,,Poster,,,,, PRIME: A Few Primitives Can Boost Robustness to Common Corruptions,Apostolos Modas (EPFL)*; Rahul Shekhar Rade (EthonAI); Guillermo Ortiz-Jimenez (EPFL); Seyed-Mohsen Moosavi-Dezfooli (Imperial College London); Pascal Frossard (EPFL),,,Poster,http://arxiv.org/abs/2112.13547,,,, AlphaVC: High-Performance and Efficient Learned Video Compression,Yibo Shi (Huawei); Yunying Ge (Huawei Technologies); Jing Wang (Huawei)*; Jue Mao (Huawei technologies),,,Poster,http://arxiv.org/abs/2207.14678,,,, Content-Oriented Learned Image Compression,"Meng Li (Huawei); Shangyin Gao (Huawei); Yihui Feng (HUAWEI Technology Co., Ltd); Yibo Shi (Huawei); Jing Wang (Huawei)*",,,Poster,http://arxiv.org/abs/2207.14168,,,, Generating Natural Images with Direct Patch Distributions Matching,Ariel Elnekave (Hebrew University of Jerusalem)*; Yair Weiss (Hebrew University),,,Poster,http://arxiv.org/abs/2203.11862,https://github.com/ariel415el/GPDM,,, -Latent Space Smoothing for Individually Fair Representations,Momchil Peychev (ETH Zurich)*; Anian Ruoss (DeepMind); Mislav Balunovic (ETH Zurich); Maximilian Baader (ETH Zürich); Martin Vechev (ETH Zurich),,,Poster,http://arxiv.org/abs/2111.13650,,,, +Latent Space Smoothing for Individually Fair Representations,Momchil Peychev (ETH Zurich)*; Anian Ruoss (DeepMind); Mislav Balunovic (ETH Zurich); Maximilian Baader (ETH Zürich); Martin Vechev (ETH Zurich),,,Poster,http://arxiv.org/abs/2111.13650,,,, SAU: Smooth activation function using convolution with approximate identities,"Koushik Biswas (Indraprastha Institute of Information Technology, New Delhi, India)*; Sandeep Kumar (Shaheed Bhagat Singh College, University of Delhi, Delhi); Shilpak Banerjee (Indian Institute of Technology Tirupati); Ashish Kumar Pandey (Indraprastha Institute of Information Technology, New Delhi, India)",,,Poster,http://arxiv.org/abs/2109.13210,,,, TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments,Shubham Dokania (IIIT Hyderabad)*; Anbumani Subramanian (IIIT-Hyderabad); Manmohan Chandraker (UC San Diego); C.V. Jawahar (IIIT-Hyderabad),,,Poster,http://arxiv.org/abs/2208.07943,https://github.com/shubham1810/trove_toolkit,,, Motion Sensitive Contrastive Learning for Self-supervised Video Representation,"JingCheng Ni (Behang University)*; Nan Zhou (Beihang University); Jie Qin (Nanjing University of Aeronautics and Astronautics); Qian Wu (Megvii); Junqi Liu (Megvii); Boxun Li (Megvii Inc.); Di Huang (Beihang University, China)",,,Poster,http://arxiv.org/abs/2208.06105,,,, @@ -1606,15 +1604,15 @@ Towards Efficient and Effective Self-Supervised Learning of Visual Representatio TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning,Haoquan Li (Southern University of Science and Technology)*; Laoming Zhang (Southern University of Science and Technology); Daoan Zhang (Southern University of Science and Technology); Lang Fu (Southern University of Science and Technology); Peng Yang (Southern University of Science and Technology); Jianguo Zhang (Southern University of Science and Technology),,,Poster,,,,, Rotation Regularization Without Rotation,Takumi Kobayashi (National Institute of Advanced Industrial Science and Technology)*,,,Poster,,,,, Parameterized Temperature Scaling for Boosting the Expressive Power in Post-Hoc Uncertainty Calibration,Christian Tomani (TUM)*; Daniel Cremers (TU Munich); Florian Buettner (German Cancer Research Center and Frankfurt University),,,Poster,http://arxiv.org/abs/2102.12182,,,, -FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations,Cemre Efe Karakas (Bogazici University); Alara Dirik (Bogazici University); Eylül Yalçınkaya (Bogazici University); Pinar Yanardag (Bogazici University)*,,,Poster,http://arxiv.org/abs/2202.06240,,,, +FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations,Cemre Efe Karakas (Bogazici University); Alara Dirik (Bogazici University); Eylül Yalçınkaya (Bogazici University); Pinar Yanardag (Bogazici University)*,,,Poster,http://arxiv.org/abs/2202.06240,,,, Dynamic Temporal Filtering in Video Models,Fuchen Long (JD.com); Zhaofan Qiu (JD.com); Yingwei Pan (JD AI Research)*; Ting Yao (JD AI Research); Chong-Wah Ngo (Singapore Management University); Tao Mei (AI Research of JD.com),,,Poster,,,,, DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimation,linzhi huang (Beijing University of Posts and Telecommunications)*; Jiahao Liang (Beijing University of Posts and Telecommunications); Weihong Deng (Beijing University of Posts and Telecommunications),,,Poster,,,,, Super-resolution 3D Human Shape from a Single Low-Resolution Image,Marco Pesavento (University of Surrey)*; Marco Volino (University of Surrey); Adrian Hilton (University of Surrey),,,Poster,http://arxiv.org/abs/2208.10738,,,, Trading Positional Complexity vs Deepness in Coordinate Networks,Jianqiao Zheng (University of Adelaide)*; Sameera Ramasinghe (University of Adelaide); Xueqian Li (Carnegie Mellon University); Simon Lucey (University of Adelaide),,,Poster,,,,, -ESS: Learning Event-based Semantic Segmentation from Still Images,"Zhaoning Sun (ETH Zürich); Nico Messikommer (University of Zurich & ETH Zurich)*; Daniel Gehrig (University of Zurich & ETH Zurich); Davide Scaramuzza (University of Zurich & ETH Zurich, Switzerland)",,,Poster,http://arxiv.org/abs/2203.10016,,,, -U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search,Ahmet Yüzügüler (EPFL)*; Nikolaos Dimitriadis (EPFL); Pascal Frossard (EPFL),,,Poster,,,,, -MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud,Michaël Ramamonjisoa (Ecole des Ponts)*; Sinisa Stekovic (Graz University of Technology); Vincent Lepetit (Ecole des Ponts ParisTech),,,Poster,http://arxiv.org/abs/2207.14268,,,, -Trapped in texture bias? A large scale comparison of deep instance segmentation,Johannes Theodoridis (Hochschule der Medien Stuttgart)*; Jessica Hofmann (Hochschule der Medien); Johannes Maucher (Media University Stuttgart); Andreas G Schilling (University of Tübingen),,,Poster,,,,, +ESS: Learning Event-based Semantic Segmentation from Still Images,"Zhaoning Sun (ETH Zürich); Nico Messikommer (University of Zurich & ETH Zurich)*; Daniel Gehrig (University of Zurich & ETH Zurich); Davide Scaramuzza (University of Zurich & ETH Zurich, Switzerland)",,,Poster,http://arxiv.org/abs/2203.10016,,,, +U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search,Ahmet Yüzügüler (EPFL)*; Nikolaos Dimitriadis (EPFL); Pascal Frossard (EPFL),,,Poster,,,,, +MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud,Michaël Ramamonjisoa (Ecole des Ponts)*; Sinisa Stekovic (Graz University of Technology); Vincent Lepetit (Ecole des Ponts ParisTech),,,Poster,http://arxiv.org/abs/2207.14268,,,, +Trapped in texture bias? A large scale comparison of deep instance segmentation,Johannes Theodoridis (Hochschule der Medien Stuttgart)*; Jessica Hofmann (Hochschule der Medien); Johannes Maucher (Media University Stuttgart); Andreas G Schilling (University of Tübingen),,,Poster,,,,, MVDG: A Unified Multi-view Framework for Domain Generalization,Jian Zhang (Nanjing University)*; Lei Qi (Southeast University); Yinghuan Shi (Nanjing University); Yang Gao (Nanjing University),,,Poster,http://arxiv.org/abs/2112.12329,,,, MINER: Multiscale Implicit Neural Representation,Vishwanath Saragadam (Rice University)*; Jasper T Tan (Rice University); Guha Balakrishnan (Rice University); Richard Baraniuk (Rice University); Ashok Veeraraghavan (Rice University),,,Poster,,,,, PTQ4ViT: Post-Training Quantization for Vision Transformers with Twin Uniform Quantization,Zhihang Yuan (Peking University)*; Chenhao Xue (Peking University); Yiqi Chen (Peking University); Qiang Wu (HOUMO.AI); Guangyu Sun (Peking University),,,Poster,,,,, @@ -1626,11 +1624,11 @@ In Defense of Image Pre-Training for Spatiotemporal Recognition,"Xianhang Li (Un SocialVAE: Human Trajectory Prediction using Timewise Latents,Pei Xu (Clemson University)*; Jean-Bernard Hayet (CIMAT); Ioannis Karamouzas (Clemson University),,,Poster,http://arxiv.org/abs/2203.08207,https://github.com/xupei0610/SocialVAE,,, "BodySLAM: Joint Camera Localisation, Mapping, and Human Motion Tracking",Dorian F Henning (Imperial College London)*; Tristan Laidlow (Imperial College London); Stefan Leutenegger (TU Munich),,,Poster,http://arxiv.org/abs/2205.02301,,,, Eliminating Gradient Conflict in Reference-based Line-Art Colorization,zekun li (University of Electronic Science and Technology of China)*; Zhengyang Geng (Peking University); Zhao Kang (University of Electronic Science and Technology of China); Wenyu Chen (University of Electronic Science and Technology of China); Yibo Yang (Peking University),,,Poster,http://arxiv.org/abs/2207.06095,https://github.com/kunkun0w0/SGA,,, -Transfer without Forgetting,"Matteo Boschini (University of Modena and Reggio Emilia)*; Lorenzo Bonicelli (Università of Modena and Reggio Emilia); Angelo Porrello (University of Modena and Reggio Emilia); Giovanni Bellitto (University of Catania); Matteo Pennisi (University of Catania); Simone Palazzo (University of Catania); Concetto Spampinato (University of Catania); SIMONE CALDERARA (University of Modena and Reggio Emilia, Italy)",,,Poster,http://arxiv.org/abs/2206.00388,,,, +Transfer without Forgetting,"Matteo Boschini (University of Modena and Reggio Emilia)*; Lorenzo Bonicelli (Università of Modena and Reggio Emilia); Angelo Porrello (University of Modena and Reggio Emilia); Giovanni Bellitto (University of Catania); Matteo Pennisi (University of Catania); Simone Palazzo (University of Catania); Concetto Spampinato (University of Catania); SIMONE CALDERARA (University of Modena and Reggio Emilia, Italy)",,,Poster,http://arxiv.org/abs/2206.00388,,,, DSR -- A dual subspace re-projection network for surface anomaly detection,Vitjan Zavrtanik (University of Ljubljana)*; Matej Kristan (University of Ljubljana); Danijel Skocaj (University of Ljubljana),,,Poster,http://arxiv.org/abs/2208.01521,,,, Multi-Exit Semantic Segmentation Networks,Alexandros Kouris (Imperial College London and Samsung AI)*; Stylianos Venieris (Samsung AI); Stefanos Laskaridis (Samsung AI); Nicholas Lane (University of Cambridge and Samsung AI),,,Poster,http://arxiv.org/abs/2106.03527,,,, Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks,Bernd Prach (IST Austria)*; Christoph H Lampert (IST Austria),,,Poster,http://arxiv.org/abs/2208.03160,https://github.com/berndprach/AOL,,, -Bridging the visual semantic gap in VLN via semantically richer instructions,Joaquín Ignacio Ossandón (Universidad Catolica de Chile)*; Benjamín Earle (Universidad Católica de Chile); Alvaro Soto (Universidad Catolica de Chile),,,Poster,,,,, +Bridging the visual semantic gap in VLN via semantically richer instructions,Joaquín Ignacio Ossandón (Universidad Catolica de Chile)*; Benjamín Earle (Universidad Católica de Chile); Alvaro Soto (Universidad Catolica de Chile),,,Poster,,,,, Kernel Relative-prototype Spectral Filtering for Few-shot Learning,"Tao Zhang (Chengdu Techman Software Co., Ltd.)*; Wu Huang (Sichuan University)",,,Poster,http://arxiv.org/abs/2207.11685,https://github.com/zhangtao2022/DSFN,,, StoryDALL-E: Adapting Pretrained Text-to-image Transformers for Story Continuation,Adyasha Maharana (UNC Chapel Hill)*; Darryl Hannan (University of North Carolina at Chapel Hill); Mohit Bansal (University of North Carolina at Chapel Hill),,,Poster,,,,, Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations,Atsuhiro Noguchi (The University of Tokyo)*; Xiao Sun (Microsoft Research Asia); Stephen Lin (Microsoft Research); Tatsuya Harada (The University of Tokyo / RIKEN),,,Poster,http://arxiv.org/abs/2204.08839,,,, @@ -1645,4 +1643,4 @@ AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimat "A Simple Approach and Benchmark for 21,000-Category Object Detection",Yutong Lin (Xi'an Jiaotong University); Chen Li (Xi'an Jiaotong University); Yue Cao (Microsoft Research); Zheng Zhang (MSRA); Jianfeng Wang (Microsoft); Lijuan Wang (Microsoft); Zicheng Liu (Microsoft); Han Hu (Microsoft Research Asia)*,,,Poster,,,,, Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach,Jiseok Youn (Seoul National University)*; Jaehun Song (Seoul National University); Hyung-Sin Kim (Seoul National University); Saewoong Bahk (Seoul National University),,,Poster,http://arxiv.org/abs/2207.10188,,,, Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection,Seong Min Kye (KAIST); Kwanghee Choi (Sogang University); Joonyoung Yi (Hyperconnect); Buru Chang (Hyperconnect)*,,,Poster,http://arxiv.org/abs/2111.14932,,,, -Online Task-free Continual Learning with Dynamic Sparse Distributed Memory,"Julien Pourcel (ENSEA)*; Ngoc-Son Vu (ETIS/Université Paris Seine, Université Cergy-Pontoise, ENSEA, CNRS/ 95000-Cergy); Robert M FRENCH (CNRS)",,,Poster,,,,, +Online Task-free Continual Learning with Dynamic Sparse Distributed Memory,"Julien Pourcel (ENSEA)*; Ngoc-Son Vu (ETIS/Université Paris Seine, Université Cergy-Pontoise, ENSEA, CNRS/ 95000-Cergy); Robert M FRENCH (CNRS)",,,Poster,,,,,