Keypoint Communities

Duncan Zauss, Sven Kreiss, Alexandre Alahi; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 11057-11066


We present a fast bottom-up method that jointly detects over 100 keypoints on humans or objects, also referred to as human/object pose estimation. We model all keypoints belonging to a human or an object --the pose-- as a graph and leverage insights from community detection to quantify the independence of keypoints. We use a graph centrality measure to assign training weights to different parts of a pose. Our proposed measure quantifies how tightly a keypoint is connected to its neighborhood. Our experiments show that our method outperforms all previous methods for human pose estimation with fine-grained keypoint annotations on the face, the hands and the feet with a total of 133 keypoints. We also show that our method generalizes to car poses.

Related Material

[pdf] [arXiv]
@InProceedings{Zauss_2021_ICCV, author = {Zauss, Duncan and Kreiss, Sven and Alahi, Alexandre}, title = {Keypoint Communities}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {11057-11066} }