{"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/integral-human-pose-regression","title":"Integral Human Pose Regression","arxiv_id":"1711.08229","date":"2017-11-22","proceeding":"ECCV 2018 9","authors":["Xiao Sun","Bin Xiao","Fangyin Wei","Shuang Liang","Yichen Wei"],"abstract":"State-of-the-art human pose estimation methods are based on heat map\nrepresentation. In spite of the good performance, the representation has a few\nissues in nature, such as not differentiable and quantization error. This work\nshows that a simple integral operation relates and unifies the heat map\nrepresentation and joint regression, thus avoiding the above issues. It is\ndifferentiable, efficient, and compatible with any heat map based methods. Its\neffectiveness is convincingly validated via comprehensive ablation experiments\nunder various settings, specifically on 3D pose estimation, for the first time.","url_abs":"http://arxiv.org/abs/1711.08229v4","url_pdf":"http://arxiv.org/pdf/1711.08229v4.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":"integral-human-pose-regression","repo_url":"https://github.com/JimmySuen/integral-human-pose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"integral-human-pose-regression","repo_url":"https://github.com/strawberryfg/c2f-3dhm-human-caffe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-mpii-human-pose","task":"Pose Estimation","dataset":"MPII Human Pose","model":"Integral Regression","rank_in_archive_order":23,"of":46,"metrics":{"PCKh-0.5":"91.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.08229","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}