{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/rethinking-keypoint-representations-modeling","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","arxiv_id":"2111.08557","date":"2021-11-16","proceeding":null,"authors":["William McNally","Kanav Vats","Alexander Wong","John McPhee"],"abstract":"In keypoint estimation tasks such as human pose estimation, heatmap-based regression is the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer from quantization error and require excessive computation to generate and post-process. Motivated to find a more efficient solution, we propose to model individual keypoints and sets of spatially related keypoints (i.e., poses) as objects within a dense single-stage anchor-based detection framework. Hence, we call our method KAPAO (pronounced \"Ka-Pow\"), for Keypoints And Poses As Objects. KAPAO is applied to the problem of single-stage multi-person human pose estimation by simultaneously detecting human pose and keypoint objects and fusing the detections to exploit the strengths of both object representations. In experiments, we observe that KAPAO is faster and more accurate than previous methods, which suffer greatly from heatmap post-processing. The accuracy-speed trade-off is especially favourable in the practical setting when not using test-time augmentation. Source code: https://github.com/wmcnally/kapao.","url_abs":"https://arxiv.org/abs/2111.08557v4","url_pdf":"https://arxiv.org/pdf/2111.08557v4.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":"rethinking-keypoint-representations-modeling","repo_url":"https://github.com/wmcnally/kapao","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"keypoint-estimation","task_name":"Keypoint Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"KAPAO-L","rank_in_archive_order":32,"of":47,"metrics":{"AP":"70.3","AP50":"91.2","AP75":"77.8","APL":"76.8","APM":"66.3","AR":"77.7"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"KAPAO-M","rank_in_archive_order":35,"of":47,"metrics":{"AP":"68.8","AP50":"90.5","AP75":"76.5","APL":"76","APM":"64.3","AR":"76.3"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-coco-test-dev","task":"Pose Estimation","dataset":"COCO test-dev","model":"KAPAO-S","rank_in_archive_order":41,"of":47,"metrics":{"AP":"63.8","AP50":"88.4","AP75":"70.4","APL":"71.7","APM":"58.6","AR":"71.2"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset":"CrowdPose","model":"KAPAO-L","rank_in_archive_order":9,"of":12,"metrics":{"AP":"68.9","AP50":"89.4","AP75":"75.6","APM":"69.9","Test":"76.6"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset":"CrowdPose","model":"KAPAO-M","rank_in_archive_order":10,"of":12,"metrics":{"AP":"67.1","AP50":"88.8","AP75":"73.4","APM":"68.1","Test":"75.2"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset":"CrowdPose","model":"KAPAO-S","rank_in_archive_order":12,"of":12,"metrics":{"AP":"63.8","AP50":"87.7","AP75":"69.4","APM":"64.8","Test":"72.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2111.08557","atlas_url":"https://app.syntology.ai/?focus=2111.08557","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2111.08557"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2111.08557\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2111.08557"},"call":"get_concepts_for_paper(arxiv_id=\"2111.08557\")"}],"by_repo":[{"repo":"wmcnally/kapao","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a3d47c8a52e000346f5cdf4f9a248f8a9d045ec9fc651dc1c5238adf62aae56f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}