Huh's picture

1 3 1

Huh

JaesungHuh

·

https://www.robots.ox.ac.uk/~jaesung/

AI & ML interests

audio visual learning

Recent Activity

upvoted a paper 8 days ago

Large-scale Pre-training for Grounded Video Caption Generation

updated a model about 1 month ago

JaesungHuh/voxconverse_pipeline

updated a model about 1 month ago

JaesungHuh/voxconverse_pipeline

View all activity

Organizations

None yet

JaesungHuh's activity

upvoted a paper 8 days ago

Large-scale Pre-training for Grounded Video Caption Generation

Paper • 2503.10781 • Published 13 days ago • 16

upvoted 2 papers 7 months ago

WhisperX: Time-Accurate Speech Transcription of Long-Form Audio

Paper • 2303.00747 • Published Mar 1, 2023 • 5

The VoxCeleb Speaker Recognition Challenge: A Retrospective

Paper • 2408.14886 • Published Aug 27, 2024 • 10