{"url":"/dataset/crowdpose","name":"CrowdPose","full_name":"CrowdPose","description_markdown":"The **CrowdPose** dataset contains about 20,000 images and a total of 80,000 human poses with 14 labeled keypoints. The test set includes 8,000 images. The crowded images containing homes are extracted from MSCOCO, MPII and AI Challenger.\r\n\r\nSource: [Human Pose Estimation for Real-World Crowded Scenarios](https://arxiv.org/abs/1907.06922)\r\nImage Source: [https://github.com/Jeff-sjtu/CrowdPose](https://github.com/Jeff-sjtu/CrowdPose)","description_withheld":null,"homepage":"https://github.com/Jeff-sjtu/CrowdPose","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/crowdpose-efficient-crowded-scenes-pose","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","first_author":"Jiefeng Li","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Pose Estimation","url":"/task/pose-estimation","datasets_with_task":"/datasets/task/pose-estimation"},{"name":"Multi-Person Pose Estimation","url":"/task/multi-person-pose-estimation","datasets_with_task":"/datasets/task/multi-person-pose-estimation"}],"languages":[{"name":"Chinese","url":"/datasets/language/chinese"}],"variants":["CrowdPose"],"data_loaders":[{"repo":"https://github.com/open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose/blob/master/docs/tasks/2d_body_keypoint.md#crowdpose","frameworks":["pytorch"]},{"repo":"https://github.com/Jeff-sjtu/CrowdPose","url":"https://github.com/Jeff-sjtu/CrowdPose","frameworks":["pytorch"]},{"repo":"https://github.com/Graviti-AI/datasets","url":"https://gas.graviti.com/dataset/hellodataset/CrowdPose","frameworks":["tf","pytorch"]}],"num_papers_in_archive":99,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-person-pose-estimation-on-crowdpose","task":"Multi-Person Pose Estimation","dataset_variant":"CrowdPose","rows":28,"metrics":["mAP @0.5:0.95","AP Easy","AP Medium","AP Hard","FPS"],"first_row_in_archive_order":{"model":"RTMO-l","paper":"/paper/rtmo-towards-high-performance-one-stage-real","metrics":{"AP Easy":"88.8","AP Hard":"77.2","AP Medium":"84.7","FPS":"52.4","mAP @0.5:0.95":"83.8"},"code_links":[{"title":"open-mmlab/mmpose","url":"https://github.com/open-mmlab/mmpose"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/pose-estimation-on-crowdpose","task":"Pose Estimation","dataset_variant":"CrowdPose","rows":12,"metrics":["AP","AP50","AP75","APM","Test","AP Hard","AP Easy","AP Medium"],"first_row_in_archive_order":{"model":"BUCTD-W48 (w/cond. input from PETR, and generative sampling)","paper":"/paper/rethinking-pose-estimation-in-crowds","metrics":{"AP":"78.5","AP Easy":"83.9","AP Hard":"72.3","AP Medium":"79.0"},"code_links":[{"title":"amathislab/BUCTD","url":"https://github.com/amathislab/BUCTD"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":5,"code_links":1,"syntology":null},{"paper":"/paper/rtmo-towards-high-performance-one-stage-real","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","date":"2023-12-12","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-pose-estimation-in-crowds","title":"Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity","date":"2023-06-13","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/explicit-box-detection-unifies-end-to-end","title":"Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation","date":"2023-02-03","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/self-constrained-inference-optimization-on","title":"Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation","date":"2022-07-06","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/i-2r-net-intra-and-inter-human-relation","title":"I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation","date":"2022-06-22","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/revealing-the-dark-secrets-of-masked-image","title":"Revealing the Dark Secrets of Masked Image Modeling","date":"2022-05-26","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":4,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lite-pose-efficient-architecture-design-for","title":"Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation","date":"2022-05-03","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/vitpose-simple-vision-transformer-baselines","title":"ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation","date":"2022-04-26","rows_on_this_dataset":1,"code_links":6,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":31,"samples_ran":18,"samples_unverified":13,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bapose-bottom-up-pose-estimation-with","title":"BAPose: Bottom-Up Pose Estimation with Disentangled Waterfall Representations","date":"2021-12-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rethinking-keypoint-representations-modeling","title":"Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation","date":"2021-11-16","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/hrformer-high-resolution-transformer-for","title":"HRFormer: High-Resolution Transformer for Dense Prediction","date":"2021-10-18","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":7,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/the-center-of-attention-center-keypoint-1","title":"The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation","date":"2021-10-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/greedy-offset-guided-keypoint-grouping-for","title":"Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation","date":"2021-07-07","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/openpifpaf-composite-fields-for-semantic","title":"OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association","date":"2021-03-03","rows_on_this_dataset":1,"code_links":6,"syntology":null},{"paper":"/paper/multi-hypothesis-pose-networks-rethinking-top","title":"Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation","date":"2021-01-27","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/transpose-towards-explainable-human-pose","title":"TransPose: Keypoint Localization via Transformer","date":"2020-12-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/scalenas-one-shot-learning-of-scale-aware","title":"ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition","date":"2020-11-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/centerhmr-a-bottom-up-single-shot-method-for","title":"Monocular, One-stage, Regression of Multiple 3D People","date":"2020-08-27","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/bottom-up-higher-resolution-networks-for","title":"HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation","date":"2019-08-27","rows_on_this_dataset":1,"code_links":19,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":27,"samples_ran":5,"samples_unverified":22,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/single-stage-multi-person-pose-machines","title":"Single-Stage Multi-Person Pose Machines","date":"2019-08-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/human-pose-estimation-for-real-world-crowded","title":"Human Pose Estimation for Real-World Crowded Scenarios","date":"2019-07-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/openpose-realtime-multi-person-2d-pose","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","date":"2018-12-18","rows_on_this_dataset":1,"code_links":51,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":16,"samples_ran":3,"samples_unverified":13,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/crowdpose-efficient-crowded-scenes-pose","title":"CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark","date":"2018-12-02","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/simple-baselines-for-human-pose-estimation","title":"Simple Baselines for Human Pose Estimation and Tracking","date":"2018-04-17","rows_on_this_dataset":1,"code_links":27,"syntology":null},{"paper":"/paper/mask-r-cnn","title":"Mask R-CNN","date":"2017-03-20","rows_on_this_dataset":1,"code_links":179,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":140,"samples_ran":42,"samples_unverified":98,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rmpe-regional-multi-person-pose-estimation","title":"RMPE: Regional Multi-person Pose Estimation","date":"2016-12-01","rows_on_this_dataset":1,"code_links":14,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":11,"samples_harvested":245,"samples_ran":89,"samples_unverified":156,"pointer_only_for_licence":32,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}