{"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/deepcut-joint-subset-partition-and-labeling","title":"DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation","arxiv_id":"1511.06645","date":"2015-11-20","proceeding":"CVPR 2016 6","authors":["Leonid Pishchulin","Eldar Insafutdinov","Siyu Tang","Bjoern Andres","Mykhaylo Andriluka","Peter Gehler","Bernt Schiele"],"abstract":"This paper considers the task of articulated human pose estimation of\nmultiple people in real world images. We propose an approach that jointly\nsolves the tasks of detection and pose estimation: it infers the number of\npersons in a scene, identifies occluded body parts, and disambiguates body\nparts between people in close proximity of each other. This joint formulation\nis in contrast to previous strategies, that address the problem by first\ndetecting people and subsequently estimating their body pose. We propose a\npartitioning and labeling formulation of a set of body-part hypotheses\ngenerated with CNN-based part detectors. Our formulation, an instance of an\ninteger linear program, implicitly performs non-maximum suppression on the set\nof part candidates and groups them to form configurations of body parts\nrespecting geometric and appearance constraints. Experiments on four different\ndatasets demonstrate state-of-the-art results for both single person and multi\nperson pose estimation. Models and code available at\nhttp://pose.mpi-inf.mpg.de.","url_abs":"http://arxiv.org/abs/1511.06645v2","url_pdf":"http://arxiv.org/pdf/1511.06645v2.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":"deepcut-joint-subset-partition-and-labeling","repo_url":"https://github.com/eldar/deepcut","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"deepcut-joint-subset-partition-and-labeling","repo_url":"https://github.com/eldar/deepcut-cnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"deepcut-joint-subset-partition-and-labeling","repo_url":"https://github.com/gsoykan/comp541_term_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deepcut-joint-subset-partition-and-labeling","repo_url":"https://github.com/gsoykan/deepercut-replication","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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-waf","task":"Multi-Person Pose Estimation","dataset":"WAF","model":"DeepCut","rank_in_archive_order":2,"of":3,"metrics":{"AOP":"86.5%"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"DeepCut","rank_in_archive_order":40,"of":46,"metrics":{"PCKh-0.5":"82.40"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06645","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}