Papers › CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark

CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark

2 Dec 2018CVPR 2019 6arXiv:1812.00324archive 2025-07-28

Jiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, Cewu Lu

Multi-person pose estimation is fundamental to many computer vision tasks and has made significant progress in recent years. However, few previous methods explored the problem of pose estimation in crowded scenes while it remains challenging and inevitable in many scenarios. Moreover, current benchmarks cannot provide an appropriate evaluation for such cases. In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms. Our model consists of two key components: joint-candidate single person pose estimation (SPPE) and global maximum joints association. With multi-peak prediction for each joint and global association using graph model, our method is robust to inevitable interference in crowded scenes and very efficient in inference. The proposed method surpasses the state-of-the-art methods on CrowdPose dataset by 5.2 mAP and results on MSCOCO dataset demonstrate the generalization ability of our method. Source code and dataset will be made publicly available.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Jeff-sjtu/CrowdPose mentioned on GitHubpytorch report
jeffffffli/CrowdPose mentioned on GitHubpytorch report
laowang666888/ECSP1 mentioned on GitHubpytorch report
open-mmlab/mmpose pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Keypoint DetectionMulti-Person Pose EstimationPose Estimation

Datasets

Introduced by this paper, per the archive.

CrowdPose

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Person Pose Estimation CrowdPose Joint-candidate SPPE + AP Easy 75.5 #17 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Joint-candidate SPPE + AP Hard 57.4 #17 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Joint-candidate SPPE + AP Medium 66.3 #17 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Joint-candidate SPPE + FPS 10.1 #17 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Joint-candidate SPPE + mAP @0.5:0.95 66.0 #17 of 28 Archive leaderboard report
Multi-Person Pose Estimation OCHuman CrowdPose AP50 40.8 #6 of 8 Archive leaderboard report
Multi-Person Pose Estimation OCHuman CrowdPose AP75 29.9 #6 of 8 Archive leaderboard report
Multi-Person Pose Estimation OCHuman CrowdPose Validation AP 27.5 #6 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections