{"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/multi-person-pose-estimation-with-local-joint","title":"Multi-Person Pose Estimation with Local Joint-to-Person Associations","arxiv_id":"1608.08526","date":"2016-08-30","proceeding":null,"authors":["Umar Iqbal","Juergen Gall"],"abstract":"Despite of the recent success of neural networks for human pose estimation,\ncurrent approaches are limited to pose estimation of a single person and cannot\nhandle humans in groups or crowds. In this work, we propose a method that\nestimates the poses of multiple persons in an image in which a person can be\noccluded by another person or might be truncated. To this end, we consider\nmulti-person pose estimation as a joint-to-person association problem. We\nconstruct a fully connected graph from a set of detected joint candidates in an\nimage and resolve the joint-to-person association and outlier detection using\ninteger linear programming. Since solving joint-to-person association jointly\nfor all persons in an image is an NP-hard problem and even approximations are\nexpensive, we solve the problem locally for each person. On the challenging\nMPII Human Pose Dataset for multiple persons, our approach achieves the\naccuracy of a state-of-the-art method, but it is 6,000 to 19,000 times faster.","url_abs":"http://arxiv.org/abs/1608.08526v2","url_pdf":"http://arxiv.org/pdf/1608.08526v2.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":"multi-person-pose-estimation-with-local-joint","repo_url":"https://github.com/MVIG-SJTU/RMPE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"keypoint-detection","task_name":"Keypoint Detection"},{"task_slug":"multi-person-pose-estimation","task_name":"Multi-Person Pose Estimation"},{"task_slug":"outlier-detection","task_name":"Outlier Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/keypoint-detection-on-mpii-multi-person","task":"Keypoint Detection","dataset":"MPII Multi-Person","model":"Local Joint-to-Person Association","rank_in_archive_order":8,"of":9,"metrics":{"mAP@0.5":"62.2%"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-mpii-multi","task":"Multi-Person Pose Estimation","dataset":"MPII Multi-Person","model":"Local Joint-to-Person Association","rank_in_archive_order":8,"of":9,"metrics":{"AP":"62.2%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1608.08526","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}