Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/CrowdPose

CrowdPose

Reported on 12 benchmarks across 4 tasks · 1 paper · 9 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Pose EstimationonOCHuman
AP50· 2018-12-02
40.8
best: 89.7 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
Pose EstimationonOCHuman
AP75· 2018-12-02
29.9
best: 80.1 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
Multi-Person Pose EstimationonOCHuman
AP50· 2018-12-02
40.8
best: 89.7 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
Multi-Person Pose EstimationonOCHuman
AP75· 2018-12-02
29.9
best: 80.1 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
Multi-Person Pose EstimationonOCHuman
Validation AP· 2018-12-02
27.5
best: 74.1 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
Pose EstimationonOCHuman
Validation AP· 2018-12-02
27.5
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324

Methodology3 results

3DonOCHuman
AP50· 2018-12-02
40.8
best: 89.7 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
3DonOCHuman
AP75· 2018-12-02
29.9
best: 80.1 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
3DonOCHuman
Validation AP· 2018-12-02
27.5
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324

Audio3 results

1 Image, 2*2 StitchionOCHuman
AP50· 2018-12-02
40.8
best: 89.7 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
1 Image, 2*2 StitchionOCHuman
AP75· 2018-12-02
29.9
best: 80.1 (MIPNet (gt-bb))
SOTA
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324
1 Image, 2*2 StitchionOCHuman
Validation AP· 2018-12-02
27.5
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark arXiv:1812.00324