Datasets › CrowdPose
CrowdPose
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.
Source: Human Pose Estimation for Real-World Crowded Scenarios Image Source: https://github.com/Jeff-sjtu/CrowdPose
Benchmarks archive 2025-07-28
All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Multi-Person Pose Estimation | CrowdPose | RTMO-l mAP @0.5:0.95 83.8 | RTMO: Towards High-Performance One-Stage Real-Time... | open-mmlab/mmpose | 28 | Compare |
| Pose Estimation | CrowdPose | BUCTD-W48 (w/cond. input from PETR, and generative sampling) AP 78.5 | Rethinking pose estimation in crowds: overcoming the... | amathislab/BUCTD | 12 | Compare |
Papers archive 2025-07-28
27 shown of 27 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 99. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
Dataset loaders archive 2025-07-28
3 loaders as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
Unknown
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- CrowdPose
1 variant name, as the archive lists them.
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