{"url":"/sota/pose-estimation-on-coco-test-dev","task":{"name":"Pose Estimation","url":"/task/pose-estimation","note":null},"dataset":{"name":"COCO test-dev","url":"/dataset/coco"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Pose Estimation** is a computer vision task where the goal is to detect the position and orientation of a person or an object. Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc. in case of Human Pose Estimation.\r\n\r\nA common benchmark for this task is [MPII Human Pose](https://paperswithcode.com/sota/pose-estimation-on-mpii-human-pose)\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose](https://github.com/Daniil-Osokin/lightweight-human-pose-estimation.pytorch) )</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","AP50","AP75","APL","APM","AR"],"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","AP50":null,"AP75":null,"APL":null,"APM":null,"AR":null}},"counts":{"rows":47,"rows_with_code":41,"rows_with_paper_page":46,"rows_dated":46,"rows_using_additional_data":5},"rows":[{"rank_in_archive_order":1,"model":"ViTPose (ViTAE-G, ensemble)","metrics":{"AP":"81.1","AP50":"95.0","AP75":"88.2","APL":"86.0","APM":"77.8","AR":"85.6"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/vitpose-simple-vision-transformer-baselines","paper_url":"https://arxiv.org/abs/2204.12484v3","paper_title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","code":"https://github.com/huggingface/transformers","n_code_links":6,"syntology":{"n_ran":18,"n_unverified":13,"n_samples":31,"n_pointer_only_licence":6}},{"rank_in_archive_order":2,"model":"ViTPose (ViTAE-G)","metrics":{"AP":"80.9","AP50":"94.8","AP75":"88.1","APL":"85.9","APM":"77.5","AR":"85.4"},"uses_additional_data":false,"paper_date":"2022-04-26","paper":"/paper/vitpose-simple-vision-transformer-baselines","paper_url":"https://arxiv.org/abs/2204.12484v3","paper_title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","code":"https://github.com/huggingface/transformers","n_code_links":6,"syntology":{"n_ran":18,"n_unverified":13,"n_samples":31,"n_pointer_only_licence":6}},{"rank_in_archive_order":3,"model":"UDP-Pose-PSA(384x288)","metrics":{"AP":"79.5","AP50":"93.6","AP75":"85.9","APL":"84.3","APM":"76.3","AR":"81.9"},"uses_additional_data":false,"paper_date":"2021-07-02","paper":"/paper/polarized-self-attention-towards-high-quality-1","paper_url":"https://arxiv.org/abs/2107.00782v2","paper_title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":6,"syntology":null},{"rank_in_archive_order":4,"model":"PoseBH-H","metrics":{"AP":"79.5","AP50":"91.9","AP75":"85.8","APL":"86.5","APM":"75.9","AR":"84.5"},"uses_additional_data":true,"paper_date":"2025-05-23","paper":"/paper/posebh-prototypical-multi-dataset-training","paper_url":"https://arxiv.org/abs/2505.17475v1","paper_title":"PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation","code":"https://github.com/uyoung-jeong/PoseBH","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"4xRSN-50 (ensemble)","metrics":{"AP":"79.2","AP50":"94.4","AP75":"87.1","APL":"76.1","APM":"83.8","AR":"84.1"},"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":6,"model":"CCM+","metrics":{"AP":"78.9","AP50":"93.8","AP75":"86","APL":"84.5","APM":"75","AR":"83.6"},"uses_additional_data":false,"paper_date":"2020-02-03","paper":"/paper/towards-high-performance-human-keypoint","paper_url":"https://arxiv.org/abs/2002.00537v2","paper_title":"Towards High Performance Human Keypoint Detection","code":"https://github.com/chaimi2013/CCM","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"UDP-Pose-PSA(256x192)","metrics":{"AP":"78.9","AP50":"93.6","AP75":"85.8","APL":"83.6","APM":"76.1","AR":"81.4"},"uses_additional_data":false,"paper_date":"2021-07-02","paper":"/paper/polarized-self-attention-towards-high-quality-1","paper_url":"https://arxiv.org/abs/2107.00782v2","paper_title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","code":"https://github.com/PaddlePaddle/PaddleSeg","n_code_links":6,"syntology":null},{"rank_in_archive_order":8,"model":"4xRSN-50","metrics":{"AP":"78.6","AP50":"94.3","AP75":"86.6","APL":"75.5","APM":"83.3","AR":"83.8"},"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":9,"model":"PCT (256x256)","metrics":{"AP":"78.3","AP50":"9","AP75":"85.9"},"uses_additional_data":false,"paper_date":"2023-03-21","paper":"/paper/human-pose-as-compositional-tokens","paper_url":"https://arxiv.org/abs/2303.11638v1","paper_title":"Human Pose as Compositional Tokens","code":"https://github.com/gengzigang/pct","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"HRNet-W48+DARK","metrics":{"AP":"77.4","AP50":"92.6","AP75":"84.6","APL":"83.7","APM":"73.6","AR":"82.3"},"uses_additional_data":false,"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":11,"model":"SwinV2-L 1K-MIM","metrics":{"AP":"77.2"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/revealing-the-dark-secrets-of-masked-image","paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","code":"https://github.com/SwinTransformer/MIM-Depth-Estimation","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"HRNet-W48 + extra data","metrics":{"AP":"77","AP50":"92.7","AP75":"84.5","APL":"83.1","APM":"73.4","AR":"82"},"uses_additional_data":false,"paper_date":"2019-02-25","paper":"/paper/deep-high-resolution-representation-learning","paper_url":"http://arxiv.org/abs/1902.09212v1","paper_title":"Deep High-Resolution Representation Learning for Human Pose Estimation","code":"https://github.com/open-mmlab/mmdetection","n_code_links":39,"syntology":{"n_ran":8,"n_unverified":17,"n_samples":25,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"EvoPose2D-L","metrics":{"AP":"76.8","AP50":"92.5","AP75":"84.3","APL":"82.5","APM":"73.5","AR":"81.7"},"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":"SwinV2-B 1K-MIM","metrics":{"AP":"76.7"},"uses_additional_data":false,"paper_date":"2022-05-26","paper":"/paper/revealing-the-dark-secrets-of-masked-image","paper_url":"https://arxiv.org/abs/2205.13543v2","paper_title":"Revealing the Dark Secrets of Masked Image Modeling","code":"https://github.com/SwinTransformer/MIM-Depth-Estimation","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":1,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"HRNet-W48+UDP","metrics":{"AP":"76.5","AP50":"92.7","AP75":"84","APL":"73.0","APM":"82.4","AR":"81.6"},"uses_additional_data":false,"paper_date":"2019-11-18","paper":"/paper/the-devil-is-in-the-details-delving-into","paper_url":"https://arxiv.org/abs/1911.07524v2","paper_title":"The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation","code":"https://github.com/open-mmlab/mmpose","n_code_links":3,"syntology":null},{"rank_in_archive_order":16,"model":"OmniPose (WASPv2)","metrics":{"AP":"76.4","AP50":"92.6","AP75":"83.7","APL":"82.6","APM":"72.6","AR":"81.2"},"uses_additional_data":false,"paper_date":"2021-03-18","paper":"/paper/omnipose-a-multi-scale-framework-for-multi","paper_url":"https://arxiv.org/abs/2103.10180v1","paper_title":"OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation","code":"https://github.com/bmartacho/OmniPose","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"HRFormer-B","metrics":{"AP":"76.2","AP50":"92.7","AP75":"83.8","APL":"82.3","APM":"72.5","AR":"81.2"},"uses_additional_data":false,"paper_date":"2021-10-18","paper":"/paper/hrformer-high-resolution-transformer-for","paper_url":"https://arxiv.org/abs/2110.09408v3","paper_title":"HRFormer: High-Resolution Transformer for Dense Prediction","code":"https://github.com/HRNet/HRFormer","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":4,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"MSPN","metrics":{"AP":"76.1","AP50":"93.4","AP75":"83.8","APL":"81.5","APM":"72.3","AR":"81.6"},"uses_additional_data":false,"paper_date":"2019-01-01","paper":"/paper/rethinking-on-multi-stage-networks-for-human","paper_url":"https://arxiv.org/abs/1901.00148v4","paper_title":"Rethinking on Multi-Stage Networks for Human Pose Estimation","code":"https://github.com/open-mmlab/mmpose","n_code_links":7,"syntology":null},{"rank_in_archive_order":19,"model":"MIPNet","metrics":{"AP":"75.7","AP50":"92.4","AP75":"83.3","APL":"81.2","APM":"71.4","AR":"80.5"},"uses_additional_data":false,"paper_date":"2021-01-27","paper":"/paper/multi-hypothesis-pose-networks-rethinking-top","paper_url":"https://arxiv.org/abs/2101.11223v3","paper_title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","code":"https://github.com/rawalkhirodkar/MIPNet","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"PPE (ResNeXt-101)","metrics":{"AP":"75.7","AP50":"90.3","AP75":"76.3","APL":"79.5","APM":"80.7"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/deep-multi-task-networks-for-occluded","paper_url":"https://arxiv.org/abs/2206.07510v2","paper_title":"Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":21,"model":"TransPose-H-A6","metrics":{"AP":"75","AP50":"92.2","AP75":"82.3","APL":"81.1","APM":"71.3"},"uses_additional_data":false,"paper_date":"2020-12-28","paper":"/paper/transpose-towards-explainable-human-pose","paper_url":"https://arxiv.org/abs/2012.14214v5","paper_title":"TransPose: Keypoint Localization via Transformer","code":"https://github.com/yangsenius/TransPose","n_code_links":1,"syntology":null},{"rank_in_archive_order":22,"model":"PoseFix","metrics":{"AP":"74.7","AP50":"91.2","AP75":"81.9","APL":"81.2","APM":"71.1","AR":"79.9"},"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":23,"model":"DPIT-L","metrics":{"AP":"74.6","AP50":"91.9","AP75":"82.1","APL":"80.6","APM":"71.3","AR":"79.9"},"uses_additional_data":false,"paper_date":"2022-09-02","paper":"/paper/dpit-dual-pipeline-integrated-transformer-for","paper_url":"https://arxiv.org/abs/2209.02431v1","paper_title":"DPIT: Dual-Pipeline Integrated Transformer for Human Pose Estimation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"S-ViPNAS-HRNetW32","metrics":{"AP":"73.9","AP50":"91.7","AP75":"82","APL":"79.5","APM":"70.5","AR":"80.4"},"uses_additional_data":false,"paper_date":"2021-05-21","paper":"/paper/vipnas-efficient-video-pose-estimation-via","paper_url":"https://arxiv.org/abs/2105.10154v1","paper_title":"ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search","code":"https://github.com/open-mmlab/mmpose","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"Flow-based (ResNet-152)","metrics":{"AP":"73.7","AP50":"91.9","AP75":"81.1","APL":"80","APM":"70.3","AR":"79"},"uses_additional_data":false,"paper_date":"2018-04-17","paper":"/paper/simple-baselines-for-human-pose-estimation","paper_url":"http://arxiv.org/abs/1804.06208v2","paper_title":"Simple Baselines for Human Pose Estimation and Tracking","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":27,"syntology":null},{"rank_in_archive_order":26,"model":"CPN+ [6, 9]","metrics":{"AP":"73.0","AP50":"91.7","AP75":"80.9","APL":"78.1","AR":"79.0"},"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":27,"model":"RMPE++","metrics":{"AP":"72.3","AP50":"89.2","AP75":"79.1","APL":"78.6","APM":"68.0"},"uses_additional_data":false,"paper_date":"2016-12-01","paper":"/paper/rmpe-regional-multi-person-pose-estimation","paper_url":"http://arxiv.org/abs/1612.00137v5","paper_title":"RMPE: Regional Multi-person Pose Estimation","code":"https://github.com/MVIG-SJTU/AlphaPose","n_code_links":14,"syntology":null},{"rank_in_archive_order":28,"model":"TFPose (ND=6 ResNet-50)","metrics":{"AP":"72.2","AP50":"90.9","AP75":"80.1","APL":"78.8","APM":"69.1"},"uses_additional_data":false,"paper_date":"2021-03-29","paper":"/paper/2103-15320","paper_url":"https://arxiv.org/abs/2103.15320v1","paper_title":"TFPose: Direct Human Pose Estimation with Transformers","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":29,"model":"CPN","metrics":{"AP":"72.1","AP50":"91.4","AP75":"80.0","APL":"77.2","AR":"78.5"},"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":30,"model":"LOGO-CAP (Ours) HRNet-W48","metrics":{"AP":"70.8"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"Dite-HRNet-30","metrics":{"AP":"70.6","AP50":"90.8","AP75":"78.2","APL":"76.1","APM":"67.4","AR":"76.4"},"uses_additional_data":false,"paper_date":"2022-04-22","paper":"/paper/dite-hrnet-dynamic-lightweight-high","paper_url":"https://arxiv.org/abs/2204.10762v3","paper_title":"Dite-HRNet: Dynamic Lightweight High-Resolution Network for Human Pose Estimation","code":"https://github.com/ziyizhang27/dite-hrnet","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"KAPAO-L","metrics":{"AP":"70.3","AP50":"91.2","AP75":"77.8","APL":"76.8","APM":"66.3","AR":"77.7"},"uses_additional_data":false,"paper_date":"2021-11-16","paper":"/paper/rethinking-keypoint-representations-modeling","paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","code":"https://github.com/wmcnally/kapao","n_code_links":1,"syntology":null},{"rank_in_archive_order":33,"model":"S-ViPNAS-Res50","metrics":{"AP":"70.3","AP50":"90.7","AP75":"78.8","APL":"75.5","APM":"67.3","AR":"77.3"},"uses_additional_data":false,"paper_date":"2021-05-21","paper":"/paper/vipnas-efficient-video-pose-estimation-via","paper_url":"https://arxiv.org/abs/2105.10154v1","paper_title":"ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search","code":"https://github.com/open-mmlab/mmpose","n_code_links":4,"syntology":{"n_ran":0,"n_unverified":8,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":34,"model":"Lite-HRNet-30","metrics":{"AP":"69.7","AP50":"90.7","AP75":"77.5","APL":"75.0","APM":"66.9","AR":"75.4"},"uses_additional_data":true,"paper_date":"2021-04-13","paper":"/paper/lite-hrnet-a-lightweight-high-resolution","paper_url":"https://arxiv.org/abs/2104.06403v1","paper_title":"Lite-HRNet: A Lightweight High-Resolution Network","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":17,"syntology":{"n_ran":12,"n_unverified":17,"n_samples":29,"n_pointer_only_licence":13}},{"rank_in_archive_order":35,"model":"KAPAO-M","metrics":{"AP":"68.8","AP50":"90.5","AP75":"76.5","APL":"76","APM":"64.3","AR":"76.3"},"uses_additional_data":false,"paper_date":"2021-11-16","paper":"/paper/rethinking-keypoint-representations-modeling","paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","code":"https://github.com/wmcnally/kapao","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"Simple Pose","metrics":{"AP":"68.1","APL":"70.5","APM":"66.8","AR":"88.2"},"uses_additional_data":true,"paper_date":"2019-11-24","paper":"/paper/simple-pose-rethinking-and-improving-a-bottom","paper_url":"https://arxiv.org/abs/1911.10529v1","paper_title":"Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation","code":"https://github.com/osmr/imgclsmob","n_code_links":8,"syntology":null},{"rank_in_archive_order":37,"model":"Lite-HRNet-18","metrics":{"AP":"66.9","AP50":"89.4","AP75":"74.4","APL":"72.2","APM":"64.0","AR":"72.6"},"uses_additional_data":false,"paper_date":"2021-04-13","paper":"/paper/lite-hrnet-a-lightweight-high-resolution","paper_url":"https://arxiv.org/abs/2104.06403v1","paper_title":"Lite-HRNet: A Lightweight High-Resolution Network","code":"https://github.com/PaddlePaddle/PaddleDetection","n_code_links":17,"syntology":{"n_ran":12,"n_unverified":17,"n_samples":29,"n_pointer_only_licence":13}},{"rank_in_archive_order":38,"model":"G-RMI","metrics":{"AP":"64.9","AP50":"85.5","AP75":"71.3","APL":"70.0","AR":"69.7"},"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":39,"model":"Faster R-CNN (ImageNet+300M)","metrics":{"AP":"64.4","AP50":"85.7","AP75":"70.7","APL":"69.8","APM":"61.8"},"uses_additional_data":true,"paper_date":"2017-07-10","paper":"/paper/revisiting-unreasonable-effectiveness-of-data","paper_url":"http://arxiv.org/abs/1707.02968v2","paper_title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","code":"https://github.com/Tencent/tencent-ml-images","n_code_links":2,"syntology":null},{"rank_in_archive_order":40,"model":"OpenPose","metrics":{"AP":"64.2","AP50":"86.2","AP75":"70.1","APL":"68.8","APM":"61"},"uses_additional_data":true,"paper_date":"2018-12-18","paper":"/paper/openpose-realtime-multi-person-2d-pose","paper_url":"https://arxiv.org/abs/1812.08008v2","paper_title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","code":"https://github.com/CMU-Perceptual-Computing-Lab/openpose","n_code_links":51,"syntology":{"n_ran":3,"n_unverified":13,"n_samples":16,"n_pointer_only_licence":2}},{"rank_in_archive_order":41,"model":"KAPAO-S","metrics":{"AP":"63.8","AP50":"88.4","AP75":"70.4","APL":"71.7","APM":"58.6","AR":"71.2"},"uses_additional_data":false,"paper_date":"2021-11-16","paper":"/paper/rethinking-keypoint-representations-modeling","paper_url":"https://arxiv.org/abs/2111.08557v4","paper_title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","code":"https://github.com/wmcnally/kapao","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"DirectPose (ResNet-101)","metrics":{"AP":"63.3","AP50":"86.7","AP75":"69.4","APL":"71.2","APM":"57.8"},"uses_additional_data":false,"paper_date":"2019-11-18","paper":"/paper/directpose-direct-end-to-end-multi-person","paper_url":"https://arxiv.org/abs/1911.07451v2","paper_title":"DirectPose: Direct End-to-End Multi-Person Pose Estimation","code":"https://github.com/aim-uofa/adet","n_code_links":9,"syntology":null},{"rank_in_archive_order":43,"model":"Mask-RCNN","metrics":{"AP":"63.1","AP50":"87.3","AP75":"68.7","APL":"71.4"},"uses_additional_data":false,"paper_date":"2017-03-20","paper":"/paper/mask-r-cnn","paper_url":"http://arxiv.org/abs/1703.06870v3","paper_title":"Mask R-CNN","code":"https://github.com/tensorflow/models/tree/master/official/vision","n_code_links":179,"syntology":{"n_ran":42,"n_unverified":98,"n_samples":140,"n_pointer_only_licence":23}},{"rank_in_archive_order":44,"model":"CMU-Pose","metrics":{"AP":"61.8","AP50":"84.9","AP75":"67.5","APL":"68.2","APM":"57.1","AR":"66.5"},"uses_additional_data":false,"paper_date":"2016-11-24","paper":"/paper/realtime-multi-person-2d-pose-estimation","paper_url":"http://arxiv.org/abs/1611.08050v2","paper_title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","code":"https://github.com/CMU-Perceptual-Computing-Lab/openpose","n_code_links":61,"syntology":{"n_ran":4,"n_unverified":19,"n_samples":23,"n_pointer_only_licence":4}},{"rank_in_archive_order":45,"model":"RMPE","metrics":{"AP":"61.8","AP50":"83.7","AP75":"69.8","APL":"67.6","APM":"58.6"},"uses_additional_data":false,"paper_date":"2016-12-01","paper":"/paper/rmpe-regional-multi-person-pose-estimation","paper_url":"http://arxiv.org/abs/1612.00137v5","paper_title":"RMPE: Regional Multi-person Pose Estimation","code":"https://github.com/MVIG-SJTU/AlphaPose","n_code_links":14,"syntology":null},{"rank_in_archive_order":46,"model":"yolopose","metrics":{"AP50":"90.3"},"uses_additional_data":false,"paper_date":"2022-04-14","paper":"/paper/yolo-pose-enhancing-yolo-for-multi-person","paper_url":"https://arxiv.org/abs/2204.06806v1","paper_title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","code":"https://github.com/texasinstruments/edgeai-yolov5","n_code_links":2,"syntology":null},{"rank_in_archive_order":47,"model":"CCNet (ViTPose)","metrics":{"AP":"-","AP50":"-","AP75":"-","APL":"-","APM":"-","AR":"-"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/on-the-calibration-of-human-pose-estimation","paper_url":"https://arxiv.org/abs/2311.17105v1","paper_title":"On the Calibration of Human Pose Estimation","code":null,"n_code_links":0,"syntology":null}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"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":19,"rows_with_any_sample_ran":17,"distinct_papers_with_graph_line":14,"distinct_papers_with_any_sample_ran":13,"samples_over_distinct_papers":{"n_ran":109,"n_unverified":195,"n_samples":304,"n_pointer_only_licence":48,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":145,"n_unverified":235,"n_samples":380,"n_pointer_only_licence":67,"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"}}}