{"url":"/task/2d-pose-estimation","name":"2D Pose Estimation","slug":"2d-pose-estimation","description_markdown":"detective pose","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":90,"papers_with_code":46,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":14,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/2d-pose-estimation-on-irodent","slug":"2d-pose-estimation-on-irodent","dataset":"iRodent","dataset_url":"/dataset/irodent","rows_in_archive":8,"metrics":["Average mAP"],"first_row_in_archive_order":{"model":"fine-tuned HRNetw32 pretrained on SuperAnimal (1 fac of data)","paper_title":"SuperAnimal pretrained pose estimation models for behavioral analysis","paper_url":"/paper/panoptic-animal-pose-estimators-are-zero-shot","paper_date":"2022-03-14","arxiv_id":"2203.07436","code_links":[{"title":"AlexEMG/DeepLabCut","url":"https://github.com/AlexEMG/DeepLabCut"},{"title":"DeepLabCut/DeepLabCut","url":"https://github.com/DeepLabCut/DeepLabCut"},{"title":"adaptivemotorcontrollab/modelzoo-figures","url":"https://github.com/adaptivemotorcontrollab/modelzoo-figures"}],"syntology":null}},{"leaderboard":"/sota/2d-pose-estimation-on-mp-100","slug":"2d-pose-estimation-on-mp-100","dataset":"MP-100","dataset_url":"/dataset/mp-100","rows_in_archive":6,"metrics":["Mean PCK@0.2 - 1shot","Mean PCK@0.2 - 5shot"],"first_row_in_archive_order":{"model":"CapeLLM","paper_title":"CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models","paper_url":"/paper/capellm-support-free-category-agnostic-pose","paper_date":"2024-11-11","arxiv_id":"2411.06869","code_links":[],"syntology":null}},{"leaderboard":"/sota/2d-pose-estimation-on-300w","slug":"2d-pose-estimation-on-300w","dataset":"300W","dataset_url":"/dataset/300w","rows_in_archive":1,"metrics":["Mean PCK@0.2"],"first_row_in_archive_order":{"model":"UniPose","paper_title":"X-Pose: Detecting Any Keypoints","paper_url":"/paper/unipose-detecting-any-keypoints","paper_date":"2023-10-12","arxiv_id":"2310.08530","code_links":[{"title":"idea-research/x-pose","url":"https://github.com/idea-research/x-pose"},{"title":"IDEA-Research/UniPose","url":"https://github.com/IDEA-Research/UniPose"}],"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":13}}},{"leaderboard":"/sota/2d-pose-estimation-on-animal-kingdom","slug":"2d-pose-estimation-on-animal-kingdom","dataset":"Animal Kingdom","dataset_url":"/dataset/animal-kingdom","rows_in_archive":1,"metrics":["Mean PCK@0.2","PCK@0.05"],"first_row_in_archive_order":{"model":"UniPose","paper_title":"X-Pose: Detecting Any Keypoints","paper_url":"/paper/unipose-detecting-any-keypoints","paper_date":"2023-10-12","arxiv_id":"2310.08530","code_links":[{"title":"idea-research/x-pose","url":"https://github.com/idea-research/x-pose"},{"title":"IDEA-Research/UniPose","url":"https://github.com/IDEA-Research/UniPose"}],"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":13}}},{"leaderboard":"/sota/2d-pose-estimation-on-desert-locust","slug":"2d-pose-estimation-on-desert-locust","dataset":"Desert Locust","dataset_url":"/dataset/desert-locust","rows_in_archive":1,"metrics":["Mean PCK@0.2"],"first_row_in_archive_order":{"model":"UniPose","paper_title":"X-Pose: Detecting Any Keypoints","paper_url":"/paper/unipose-detecting-any-keypoints","paper_date":"2023-10-12","arxiv_id":"2310.08530","code_links":[{"title":"idea-research/x-pose","url":"https://github.com/idea-research/x-pose"},{"title":"IDEA-Research/UniPose","url":"https://github.com/IDEA-Research/UniPose"}],"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":13}}},{"leaderboard":"/sota/2d-pose-estimation-on-harper","slug":"2d-pose-estimation-on-harper","dataset":"HARPER","dataset_url":"/dataset/harper","rows_in_archive":1,"metrics":["PCK"],"first_row_in_archive_order":{"model":"HRNet","paper_title":"Deep High-Resolution Representation Learning for Human Pose Estimation","paper_url":"/paper/deep-high-resolution-representation-learning","paper_date":"2019-02-25","arxiv_id":"1902.09212","code_links":[{"title":"open-mmlab/mmdetection","url":"https://github.com/open-mmlab/mmdetection"},{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"},{"title":"leoxiaobin/deep-high-resolution-net.pytorch","url":"https://github.com/leoxiaobin/deep-high-resolution-net.pytorch"},{"title":"HRNet/HRNet-Semantic-Segmentation","url":"https://github.com/HRNet/HRNet-Semantic-Segmentation"},{"title":"osmr/imgclsmob","url":"https://github.com/osmr/imgclsmob"},{"title":"Microsoft/human-pose-estimation.pytorch","url":"https://github.com/Microsoft/human-pose-estimation.pytorch"},{"title":"HRNet/HRNet-Facial-Landmark-Detection","url":"https://github.com/HRNet/HRNet-Facial-Landmark-Detection"},{"title":"HRNet/HRNet-Image-Classification","url":"https://github.com/HRNet/HRNet-Image-Classification"},{"title":"HRNet/HRNet-Object-Detection","url":"https://github.com/HRNet/HRNet-Object-Detection"},{"title":"mindspore-lab/mindone","url":"https://github.com/mindspore-lab/mindone"},{"title":"leeyegy/SimDR","url":"https://github.com/leeyegy/SimDR"},{"title":"leeyegy/simcc","url":"https://github.com/leeyegy/simcc"},{"title":"mks0601/PoseFix_RELEASE","url":"https://github.com/mks0601/PoseFix_RELEASE"},{"title":"HRNet/HRNet-Human-Pose-Estimation","url":"https://github.com/HRNet/HRNet-Human-Pose-Estimation"},{"title":"strivebo/image_segmentation_dl","url":"https://github.com/strivebo/image_segmentation_dl"},{"title":"HRNet/HRNet-MaskRCNN-Benchmark","url":"https://github.com/HRNet/HRNet-MaskRCNN-Benchmark"},{"title":"CASIA-IVA-Lab/ISP-reID","url":"https://github.com/CASIA-IVA-Lab/ISP-reID"},{"title":"NVlabs/PAMTRI","url":"https://github.com/NVlabs/PAMTRI"},{"title":"k-miran/hear","url":"https://github.com/k-miran/hear"},{"title":"Vill-Lab/2022-TIP-HCGA","url":"https://github.com/Vill-Lab/2022-TIP-HCGA"},{"title":"d-shivam/Pose-estimation-based-action-recognition-for-help-Situation-Identification","url":"https://github.com/d-shivam/Pose-estimation-based-action-recognition-for-help-Situation-Identification"},{"title":"chuanqichen/deepcoaching","url":"https://github.com/chuanqichen/deepcoaching"},{"title":"Mary-xl/HRnet_Kaggle_iNat2019_FGVC","url":"https://github.com/Mary-xl/HRnet_Kaggle_iNat2019_FGVC"},{"title":"v1viswan/Domain_adaptation_in_HRNet","url":"https://github.com/v1viswan/Domain_adaptation_in_HRNet"},{"title":"ken724049/action-recognition","url":"https://github.com/ken724049/action-recognition"},{"title":"NU-LL/lighttrack-","url":"https://github.com/NU-LL/lighttrack-"},{"title":"thoughtmachines/Human-Pose-Estimation-using-HRNets","url":"https://github.com/thoughtmachines/Human-Pose-Estimation-using-HRNets"},{"title":"ducongju/HRNet","url":"https://github.com/ducongju/HRNet"},{"title":"thomasslloyd/FitSpatial","url":"https://github.com/thomasslloyd/FitSpatial"},{"title":"laowang666888/HRNET","url":"https://github.com/laowang666888/HRNET"},{"title":"baoshengyu/deep-high-resolution-net.pytorch","url":"https://github.com/baoshengyu/deep-high-resolution-net.pytorch"},{"title":"sdll/hrnet-pose-estimation","url":"https://github.com/sdll/hrnet-pose-estimation"},{"title":"gox-ai/hrnet-pose-api","url":"https://github.com/gox-ai/hrnet-pose-api"},{"title":"anshky/HR-NET","url":"https://github.com/anshky/HR-NET"},{"title":"wsjzha/deep-high-resolution-net.pytorch","url":"https://github.com/wsjzha/deep-high-resolution-net.pytorch"},{"title":"visionNoob/hrnet_pytorch","url":"https://github.com/visionNoob/hrnet_pytorch"},{"title":"abhi1kumar/hrnet_pose_single_gpu","url":"https://github.com/abhi1kumar/hrnet_pose_single_gpu"},{"title":"goutern/PoseEstimation","url":"https://github.com/goutern/PoseEstimation"}],"syntology":{"n":25,"n_ran":8,"n_unverified":17,"n_pointer_only":0}}},{"leaderboard":"/sota/2d-pose-estimation-on-human3-6m","slug":"2d-pose-estimation-on-human3-6m","dataset":"Human3.6M","dataset_url":"/dataset/human3-6m","rows_in_archive":1,"metrics":["EPE"],"first_row_in_archive_order":{"model":"UniHCP (finetune)","paper_title":"UniHCP: A Unified Model for Human-Centric Perceptions","paper_url":"/paper/unihcp-a-unified-model-for-human-centric","paper_date":"2023-03-06","arxiv_id":"2303.02936","code_links":[{"title":"opengvlab/unihcp","url":"https://github.com/opengvlab/unihcp"}],"syntology":{"n":13,"n_ran":7,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/2d-pose-estimation-on-macaquepose","slug":"2d-pose-estimation-on-macaquepose","dataset":"MacaquePose","dataset_url":"/dataset/macaquepose","rows_in_archive":1,"metrics":["AP"],"first_row_in_archive_order":{"model":"UniPose","paper_title":"X-Pose: Detecting Any Keypoints","paper_url":"/paper/unipose-detecting-any-keypoints","paper_date":"2023-10-12","arxiv_id":"2310.08530","code_links":[{"title":"idea-research/x-pose","url":"https://github.com/idea-research/x-pose"},{"title":"IDEA-Research/UniPose","url":"https://github.com/IDEA-Research/UniPose"}],"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":13}}},{"leaderboard":"/sota/2d-pose-estimation-on-vinegar-fly","slug":"2d-pose-estimation-on-vinegar-fly","dataset":"Vinegar Fly","dataset_url":"/dataset/vinegar-fly","rows_in_archive":1,"metrics":["Mean PCK@0.2"],"first_row_in_archive_order":{"model":"UniPose","paper_title":"X-Pose: Detecting Any Keypoints","paper_url":"/paper/unipose-detecting-any-keypoints","paper_date":"2023-10-12","arxiv_id":"2310.08530","code_links":[{"title":"idea-research/x-pose","url":"https://github.com/idea-research/x-pose"},{"title":"IDEA-Research/UniPose","url":"https://github.com/IDEA-Research/UniPose"}],"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":13}}}],"datasets":[{"url":"/dataset/human3-6m","name":"Human3.6M","full_name":"","num_papers_in_archive":783},{"url":"/dataset/300w","name":"300W","full_name":"300 Faces-In-The-Wild","num_papers_in_archive":206},{"url":"/dataset/animal-kingdom","name":"Animal Kingdom","full_name":"","num_papers_in_archive":26},{"url":"/dataset/mp-100","name":"MP-100","full_name":"Mulit-category Pose Dataset","num_papers_in_archive":12},{"url":"/dataset/harper","name":"HARPER","full_name":"Exploring 3D Human Pose Estimation and Forecasting from the Robot’s Perspective: The HARPER Dataset","num_papers_in_archive":5},{"url":"/dataset/3d-pop","name":"3D-POP","full_name":"","num_papers_in_archive":3},{"url":"/dataset/irodent","name":"iRodent","full_name":"iRodent Animal Pose Estimation","num_papers_in_archive":2},{"url":"/dataset/slam2ref","name":"SLAM2REF","full_name":"ConSLAM BIM and GT Poses","num_papers_in_archive":2},{"url":"/dataset/superanimal-topviewmouse","name":"SuperAnimal-TopViewMouse","full_name":"","num_papers_in_archive":2},{"url":"/dataset/conslam","name":"ConSLAM","full_name":"Construction Dataset for SLAM","num_papers_in_archive":1},{"url":"/dataset/darai","name":"DARai","full_name":"Daily Activity Recordings for AI and ML applications","num_papers_in_archive":1},{"url":"/dataset/desert-locust","name":"Desert Locust","full_name":"Desert Locust","num_papers_in_archive":1},{"url":"/dataset/macaquepose","name":"MacaquePose","full_name":"MacaquePose","num_papers_in_archive":1},{"url":"/dataset/vinegar-fly","name":"Vinegar Fly","full_name":"Vinegar Fly","num_papers_in_archive":1}],"subtasks":[{"url":"/task/category-agnostic-pose-estimation","name":"Category-Agnostic Pose Estimation"},{"url":"/task/overlapping-pose-estimation","name":"Overlapping Pose Estimation"}],"parent_tasks":[{"url":"/task/2d-classification","name":"2D Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":46,"tagged_in_all":90,"items":[{"url":"/paper/realtime-multi-person-2d-pose-estimation","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","date":"2016-11-24","arxiv_id":"1611.08050","repositories_listed":61,"syntology":{"n":23,"n_ran":4,"n_unverified":19,"n_pointer_only":4}},{"url":"/paper/openpose-realtime-multi-person-2d-pose","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","date":"2018-12-18","arxiv_id":"1812.08008","repositories_listed":51,"syntology":{"n":16,"n_ran":3,"n_unverified":13,"n_pointer_only":2}},{"url":"/paper/deep-high-resolution-representation-learning","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","date":"2019-02-25","arxiv_id":"1902.09212","repositories_listed":39,"syntology":{"n":25,"n_ran":8,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","arxiv_id":"2312.00752","repositories_listed":35,"syntology":{"n":62,"n_ran":18,"n_unverified":44,"n_pointer_only":28}},{"url":"/paper/polarized-self-attention-towards-high-quality-1","title":"Polarized Self-Attention: Towards High-quality Pixel-wise Regression","date":"2021-07-02","arxiv_id":"2107.00782","repositories_listed":6,"syntology":null},{"url":"/paper/towards-3d-human-pose-estimation-in-the-wild","title":"Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach","date":"2017-04-08","arxiv_id":"1704.02447","repositories_listed":6,"syntology":null},{"url":"/paper/panoptic-animal-pose-estimators-are-zero-shot","title":"SuperAnimal pretrained pose estimation models for behavioral analysis","date":"2022-03-14","arxiv_id":"2203.07436","repositories_listed":3,"syntology":null},{"url":"/paper/sapiens-foundation-for-human-vision-models","title":"Sapiens: Foundation for Human Vision Models","date":"2024-08-22","arxiv_id":"2408.12569","repositories_listed":2,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/pose-anything-a-graph-based-approach-for","title":"A Graph-Based Approach for Category-Agnostic Pose Estimation","date":"2023-11-29","arxiv_id":"2311.17891","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/unipose-detecting-any-keypoints","title":"X-Pose: Detecting Any Keypoints","date":"2023-10-12","arxiv_id":"2310.08530","repositories_listed":2,"syntology":{"n":13,"n_ran":11,"n_unverified":2,"n_pointer_only":13}},{"url":"/paper/uplift-and-upsample-efficient-3d-human-pose","title":"Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers","date":"2022-10-12","arxiv_id":"2210.06110","repositories_listed":2,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/rotation-equivariant-siamese-networks-for","title":"Rotation Equivariant Siamese Networks for Tracking","date":"2020-12-24","arxiv_id":"2012.13078","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/simultaneously-collected-multimodal-lying","title":"Simultaneously-Collected Multimodal Lying Pose Dataset: Towards In-Bed Human Pose Monitoring under Adverse Vision Conditions","date":"2020-08-20","arxiv_id":"2008.08735","repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-train-with-synthetic-humans","title":"Learning to Train with Synthetic Humans","date":"2019-08-02","arxiv_id":"1908.00967","repositories_listed":2,"syntology":null},{"url":"/paper/detrpose-real-time-end-to-end-transformer","title":"DETRPose: Real-time end-to-end transformer model for multi-person pose estimation","date":"2025-06-16","arxiv_id":"2506.13027","repositories_listed":1,"syntology":null},{"url":"/paper/edge-weight-prediction-for-category-agnostic","title":"Edge Weight Prediction For Category-Agnostic Pose Estimation","date":"2024-11-25","arxiv_id":"2411.16665","repositories_listed":1,"syntology":null},{"url":"/paper/mpl-lifting-3d-human-pose-from-multi-view-2d","title":"MPL: Lifting 3D Human Pose from Multi-view 2D Poses","date":"2024-08-20","arxiv_id":"2408.10805","repositories_listed":1,"syntology":null},{"url":"/paper/rtmw-real-time-multi-person-2d-and-3d-whole","title":"RTMW: Real-Time Multi-Person 2D and 3D Whole-body Pose Estimation","date":"2024-07-11","arxiv_id":"2407.08634","repositories_listed":1,"syntology":null},{"url":"/paper/capex-category-agnostic-pose-estimation-from","title":"CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation","date":"2024-06-01","arxiv_id":"2406.00384","repositories_listed":1,"syntology":null},{"url":"/paper/poise-pose-guided-human-silhouette-extraction","title":"POISE: Pose Guided Human Silhouette Extraction under Occlusions","date":"2023-11-09","arxiv_id":"2311.05077","repositories_listed":1,"syntology":null},{"url":"/paper/hap-structure-aware-masked-image-modeling-for-1","title":"HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception","date":"2023-10-31","arxiv_id":"2310.20695","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_unverified":3,"n_pointer_only":6}},{"url":"/paper/rtmpose-real-time-multi-person-pose","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","date":"2023-03-13","arxiv_id":"2303.07399","repositories_listed":1,"syntology":null},{"url":"/paper/unihcp-a-unified-model-for-human-centric","title":"UniHCP: A Unified Model for Human-Centric Perceptions","date":"2023-03-06","arxiv_id":"2303.02936","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/matching-is-not-enough-a-two-stage-framework","title":"Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/2d-pose-estimation-based-child-action","title":"2D Pose Estimation based Child Action Recognition","date":"2022-12-18","arxiv_id":"2212.09027","repositories_listed":1,"syntology":null},{"url":"/paper/kinematic-aware-hierarchical-attention","title":"Kinematic-aware Hierarchical Attention Network for Human Pose Estimation in Videos","date":"2022-11-29","arxiv_id":"2211.15868","repositories_listed":1,"syntology":null},{"url":"/paper/hupr-a-benchmark-for-human-pose-estimation","title":"HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar","date":"2022-10-22","arxiv_id":"2210.12564","repositories_listed":1,"syntology":null},{"url":"/paper/pose-for-everything-towards-category-agnostic","title":"Pose for Everything: Towards Category-Agnostic Pose Estimation","date":"2022-07-21","arxiv_id":"2207.10387","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/a-unified-framework-for-domain-adaptive-pose","title":"A Unified Framework for Domain Adaptive Pose Estimation","date":"2022-04-01","arxiv_id":"2204.00172","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/hhp-net-a-light-heteroscedastic-neural","title":"HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty","date":"2021-11-02","arxiv_id":"2111.01440","repositories_listed":1,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}