{"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/bapose-bottom-up-pose-estimation-with","title":"BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations","arxiv_id":"2112.10716","date":"2021-12-20","proceeding":null,"authors":["Bruno Artacho","Andreas Savakis"],"abstract":"We propose BAPose, a novel bottom-up approach that achieves state-of-the-art results for multi-person pose estimation. Our end-to-end trainable framework leverages a disentangled multi-scale waterfall architecture and incorporates adaptive convolutions to infer keypoints more precisely in crowded scenes with occlusions. The multi-scale representations, obtained by the disentangled waterfall module in BAPose, leverage the efficiency of progressive filtering in the cascade architecture, while maintaining multi-scale fields-of-view comparable to spatial pyramid configurations. Our results on the challenging COCO and CrowdPose datasets demonstrate that BAPose is an efficient and robust framework for multi-person pose estimation, achieving significant improvements on state-of-the-art accuracy.","url_abs":"https://arxiv.org/abs/2112.10716v1","url_pdf":"https://arxiv.org/pdf/2112.10716v1.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":"bapose-bottom-up-pose-estimation-with","repo_url":"https://github.com/bmartacho/BAPose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"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-coco","task":"Multi-Person Pose Estimation","dataset":"COCO (Common Objects in Context)","model":"BAPose","rank_in_archive_order":5,"of":15,"metrics":{"AP":"0.727","Test AP":"71.2","Validation AP":"72.7"},"uses_additional_data":false},{"leaderboard":"/sota/multi-person-pose-estimation-on-crowdpose","task":"Multi-Person Pose Estimation","dataset":"CrowdPose","model":"BAPose (W32)","rank_in_archive_order":8,"of":28,"metrics":{"AP Easy":"79.9","AP Hard":"61.3","AP Medium":"73.4","mAP @0.5:0.95":"72.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2112.10716","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}