{"url":"/sota/multi-person-pose-estimation-on-coco","task":{"name":"Multi-Person Pose Estimation","url":"/task/multi-person-pose-estimation","note":null},"dataset":{"name":"COCO (Common Objects in Context)","url":"/dataset/coco"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Multi-person pose estimation is the task of estimating the pose of multiple people in one frame.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Human Pose Estimation with TensorFlow\r\n](https://github.com/eldar/pose-tensorflow) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["AP","Test AP","Validation AP"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"AP":"higher","Test AP":"higher","Validation AP":"higher"}},"counts":{"rows":15,"rows_with_code":13,"rows_with_paper_page":15,"rows_dated":15,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"RSN","metrics":{"AP":"0.792"},"uses_additional_data":false,"paper_date":"2020-03-09","paper":"/paper/learning-delicate-local-representations-for","paper_url":"https://arxiv.org/abs/2003.04030v3","paper_title":"Learning Delicate Local Representations for Multi-Person Pose Estimation","code":"https://github.com/open-mmlab/mmpose","n_code_links":4,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"DarkPose","metrics":{"AP":"0.774"},"uses_additional_data":true,"paper_date":"2019-10-14","paper":"/paper/distribution-aware-coordinate-representation","paper_url":"https://arxiv.org/abs/1910.06278v1","paper_title":"Distribution-Aware Coordinate Representation for Human Pose Estimation","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":6,"syntology":{"n_ran":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"UniPose","metrics":{"AP":"0.768"},"uses_additional_data":true,"paper_date":"2023-10-12","paper":"/paper/unipose-detecting-any-keypoints","paper_url":"https://arxiv.org/abs/2310.08530v2","paper_title":"X-Pose: Detecting Any Keypoints","code":"https://github.com/idea-research/x-pose","n_code_links":2,"syntology":{"n_ran":11,"n_unverified":2,"n_samples":13,"n_pointer_only_licence":13}},{"rank_in_archive_order":4,"model":"CPN+","metrics":{"AP":"0.730"},"uses_additional_data":false,"paper_date":"2017-11-20","paper":"/paper/cascaded-pyramid-network-for-multi-person","paper_url":"http://arxiv.org/abs/1711.07319v2","paper_title":"Cascaded Pyramid Network for Multi-Person Pose Estimation","code":"https://github.com/chenyilun95/tf-cpn","n_code_links":5,"syntology":null},{"rank_in_archive_order":5,"model":"BAPose","metrics":{"AP":"0.727","Test AP":"71.2","Validation AP":"72.7"},"uses_additional_data":false,"paper_date":"2021-12-20","paper":"/paper/bapose-bottom-up-pose-estimation-with","paper_url":"https://arxiv.org/abs/2112.10716v1","paper_title":"BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations","code":"https://github.com/bmartacho/BAPose","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"CenterGroup","metrics":{"AP":"0.714","Test AP":"71.4"},"uses_additional_data":false,"paper_date":"2021-10-11","paper":"/paper/the-center-of-attention-center-keypoint-1","paper_url":"https://arxiv.org/abs/2110.05132v1","paper_title":"The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation","code":"https://github.com/dvl-tum/center-group","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"OpenPifPaf","metrics":{"AP":"0.709","Test AP":"70.9","Validation AP":"71.0"},"uses_additional_data":false,"paper_date":"2021-03-03","paper":"/paper/openpifpaf-composite-fields-for-semantic","paper_url":"https://arxiv.org/abs/2103.02440v2","paper_title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","code":"https://github.com/openpifpaf/openpifpaf","n_code_links":6,"syntology":null},{"rank_in_archive_order":8,"model":"Pose Residual Network","metrics":{"AP":"0.697"},"uses_additional_data":false,"paper_date":"2018-07-11","paper":"/paper/multiposenet-fast-multi-person-pose","paper_url":"http://arxiv.org/abs/1807.04067v1","paper_title":"MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Network","code":"https://github.com/salihkaragoz/pose-residual-network-pytorch","n_code_links":4,"syntology":null},{"rank_in_archive_order":9,"model":"G-RMI*","metrics":{"AP":"0.685"},"uses_additional_data":false,"paper_date":"2017-01-06","paper":"/paper/towards-accurate-multi-person-pose-estimation","paper_url":"http://arxiv.org/abs/1701.01779v2","paper_title":"Towards Accurate Multi-person Pose Estimation in the Wild","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"Supervising Self-Attention","metrics":{"AP":"0.665"},"uses_additional_data":false,"paper_date":"2021-11-25","paper":"/paper/attend-to-who-you-are-supervising-self-1","paper_url":"https://arxiv.org/abs/2111.12892v1","paper_title":"Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association","code":"https://github.com/yangsenius/ssa","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"Associative Embedding","metrics":{"AP":"0.655"},"uses_additional_data":false,"paper_date":"2016-11-16","paper":"/paper/associative-embedding-end-to-end-learning-for","paper_url":"http://arxiv.org/abs/1611.05424v2","paper_title":"Associative Embedding: End-to-End Learning for Joint Detection and Grouping","code":"https://github.com/open-mmlab/mmpose","n_code_links":5,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"G-RMI","metrics":{"AP":"0.649"},"uses_additional_data":false,"paper_date":"2017-01-06","paper":"/paper/towards-accurate-multi-person-pose-estimation","paper_url":"http://arxiv.org/abs/1701.01779v2","paper_title":"Towards Accurate Multi-person Pose Estimation in the Wild","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":13,"model":"EvoPose2D-L","metrics":{"Test AP":"76.8","Validation AP":"77.5"},"uses_additional_data":false,"paper_date":"2020-11-17","paper":"/paper/evopose2d-pushing-the-boundaries-of-2d-human","paper_url":"https://arxiv.org/abs/2011.08446v2","paper_title":"EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer","code":"https://github.com/wmcnally/evopose2d","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"PoseFix","metrics":{"Test AP":"76.7","Validation AP":"77.3"},"uses_additional_data":false,"paper_date":"2018-12-10","paper":"/paper/posefix-model-agnostic-general-human-pose","paper_url":"http://arxiv.org/abs/1812.03595v3","paper_title":"PoseFix: Model-agnostic General Human Pose Refinement Network","code":"https://github.com/mks0601/PoseFix_RELEASE","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"LitePose-S","metrics":{"Test AP":"56.7","Validation AP":"56.8"},"uses_additional_data":false,"paper_date":"2022-05-03","paper":"/paper/lite-pose-efficient-architecture-design-for","paper_url":"https://arxiv.org/abs/2205.01271v4","paper_title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","code":"https://github.com/mit-han-lab/litepose","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":6,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":22,"n_unverified":17,"n_samples":39,"n_pointer_only_licence":13,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":22,"n_unverified":17,"n_samples":39,"n_pointer_only_licence":13,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}