{"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/the-center-of-attention-center-keypoint-1","title":"The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation","arxiv_id":"2110.05132","date":"2021-10-11","proceeding":"ICCV 2021 10","authors":["Guillem Brasó","Nikita Kister","Laura Leal-Taixé"],"abstract":"We introduce CenterGroup, an attention-based framework to estimate human poses from a set of identity-agnostic keypoints and person center predictions in an image. Our approach uses a transformer to obtain context-aware embeddings for all detected keypoints and centers and then applies multi-head attention to directly group joints into their corresponding person centers. While most bottom-up methods rely on non-learnable clustering at inference, CenterGroup uses a fully differentiable attention mechanism that we train end-to-end together with our keypoint detector. As a result, our method obtains state-of-the-art performance with up to 2.5x faster inference time than competing bottom-up methods. Our code is available at https://github.com/dvl-tum/center-group .","url_abs":"https://arxiv.org/abs/2110.05132v1","url_pdf":"https://arxiv.org/pdf/2110.05132v1.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":"the-center-of-attention-center-keypoint-1","repo_url":"https://github.com/dvl-tum/center-group","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-person-pose-estimation-on-coco","task":"Multi-Person Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"CenterGroup","rank_in_archive_order":6,"of":15,"metrics":{"AP":"0.714","Test AP":"71.4"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-crowdpose","task":"Multi-Person Pose Estimation","dataset":"CrowdPose","model":"CenterGroup","rank_in_archive_order":14,"of":28,"metrics":{"AP Easy":"76.6","AP Hard":"61.5","AP Medium":"70.0","mAP @0.5:0.95":"69.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.05132","atlas_url":"https://app.syntology.ai/?focus=2110.05132","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}