Model
ViTPose
A pose estimation model based on the Vision Transformer architecture that achieves strong performance on human and animal keypoint detection tasks. It belongs to the family of visual foundation models and has been applied across a range of body pose estimation benchmarks.
Timeline (last 90 days)
Sep 11
Vision foundation models such as DINO and ViTPose enable reasonably reliable keypoint detection results without requiring large amounts of animal-specific annotated data.
Unverified50%