190
ViTPose Transformers
⚡
Detect and estimate human poses in images and videos
ViTPose
Collection for ViTPose models based on transformers implementation.
-
-
usyd-community/vitpose-plus-small
Keypoint Detection • 0.0B • Updated • 3.37k • 3 -
usyd-community/vitpose-plus-base
Keypoint Detection • 0.1B • Updated • 222k • 15 -
usyd-community/vitpose-plus-large
Keypoint Detection • 0.4B • Updated • 9.11k • 2 -
usyd-community/vitpose-plus-huge
Keypoint Detection • 0.9B • Updated • 47k • 10 -
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation
Paper • 2204.12484 • Published • 2 -
ViTPose++: Vision Transformer for Generic Body Pose Estimation
Paper • 2212.04246 • Published • 1 -
usyd-community/vitpose-base
Keypoint Detection • 0.1B • Updated • 2.04k • 9 -
usyd-community/vitpose-base-simple
Keypoint Detection • 0.1B • Updated • 94.6k • 27 -
usyd-community/vitpose-base-coco-aic-mpii
Keypoint Detection • 0.1B • Updated • 139 • 1