{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/keypoint-communities","title":"Keypoint Communities","arxiv_id":"2110.00988","date":"2021-10-03","proceeding":"ICCV 2021 10","authors":["Duncan Zauss","Sven Kreiss","Alexandre Alahi"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2110.00988v1","url_pdf":"https://arxiv.org/pdf/2110.00988v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"keypoint-communities","repo_url":"https://github.com/duncanzauss/keypoint_communities","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"car-pose-estimation","task_name":"Car Pose Estimation"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"object","task_name":"Object"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-coco-wholebody-1","task":"2D Human Pose Estimation","dataset":"COCO-WholeBody","model":"Zauss et al.","rank_in_archive_order":9,"of":15,"metrics":{"WB":"60.4","body":"69.6","face":"85.0","foot":"63.4","hand":"52.9"},"uses_additional_data":true},{"leaderboard":"/sota/car-pose-estimation-on-apollocar3d","task":"Car Pose Estimation","dataset":"ApolloCar3D","model":"Zauss et al.","rank_in_archive_order":1,"of":3,"metrics":{"Detection Rate":"91.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.00988","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}