{"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/greedy-offset-guided-keypoint-grouping-for","title":"Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation","arxiv_id":"2107.03098","date":"2021-07-07","proceeding":null,"authors":["Jia Li","Linhua Xiang","Jiwei Chen","Zengfu Wang"],"abstract":"We propose a simple yet reliable bottom-up approach with a good trade-off between accuracy and efficiency for the problem of multi-person pose estimation. Given an image, we employ an Hourglass Network to infer all the keypoints from different persons indiscriminately as well as the guiding offsets connecting the adjacent keypoints belonging to the same persons. Then, we greedily group the candidate keypoints into multiple human poses (if any), utilizing the predicted guiding offsets. And we refer to this process as greedy offset-guided keypoint grouping (GOG). Moreover, we revisit the encoding-decoding method for the multi-person keypoint coordinates and reveal some important facts affecting accuracy. Experiments have demonstrated the obvious performance improvements brought by the introduced components. Our approach is comparable to the state of the art on the challenging COCO dataset under fair conditions. The source code and our pre-trained model are publicly available online.","url_abs":"https://arxiv.org/abs/2107.03098v2","url_pdf":"https://arxiv.org/pdf/2107.03098v2.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":"greedy-offset-guided-keypoint-grouping-for","repo_url":"https://github.com/hellojialee/OffsetGuided","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-person-pose-estimation-on-coco-test-dev","task":"Multi-Person Pose Estimation","dataset":"COCO test-dev","model":"Hourglass-104","rank_in_archive_order":12,"of":15,"metrics":{"AP":"65.6","APL":"68.8","APM":"63.3"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-crowdpose","task":"Multi-Person Pose Estimation","dataset":"CrowdPose","model":"Hourglass-104","rank_in_archive_order":19,"of":28,"metrics":{"AP Easy":"73.8","AP Hard":"54.8","AP Medium":"66.2","FPS":"14.7 (21.4)","mAP @0.5:0.95":"65.2"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset":"CrowdPose","model":"Hourglass-104","rank_in_archive_order":11,"of":12,"metrics":{"AP":"65.2","AP50":"85.9","AP75":"69.5","APM":"66.2"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}