Collected sources and patterns will appear here. Add from search or the patterns library.
Image -> List<PoseKeypoints>
Detect all candidate keypoints globally across an image and group them into distinct instances using spatial affinity scores.
Problem it solves
Instance-level bounding boxes fail when subjects overlap heavily or are highly occluded.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.