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/PoseBH-H

PoseBH-H

Reported on 24 benchmarks across 3 tasks · 1 paper · 3 SOTA

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

Computer Vision8 results

Pose EstimationonCOCO test-dev
APL· uses extra data· 2025-05-23
86.5
SOTA
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
Pose EstimationonOCHuman
Test AP· uses extra data· 2025-05-23
87
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
Pose EstimationonOCHuman
Validation AP· uses extra data· 2025-05-23
86
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
Pose EstimationonCOCO test-dev
AP· uses extra data· 2025-05-23
79.5
best: 81.1 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
Pose EstimationonCOCO test-dev
AP50· uses extra data· 2025-05-23
91.9
best: 95 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
Pose EstimationonCOCO test-dev
AP75· uses extra data· 2025-05-23
85.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
Pose EstimationonCOCO test-dev
APM· uses extra data· 2025-05-23
75.9
best: 83.8 (4xRSN-50 (ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
Pose EstimationonCOCO test-dev
AR· uses extra data· 2025-05-23
84.5
best: 88.2 (Simple Pose)
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475

Methodology8 results

3DonCOCO test-dev
APL· uses extra data· 2025-05-23
86.5
SOTA
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
3DonOCHuman
Test AP· uses extra data· 2025-05-23
87
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
3DonOCHuman
Validation AP· uses extra data· 2025-05-23
86
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
3DonCOCO test-dev
AP· uses extra data· 2025-05-23
79.5
best: 81.1 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
3DonCOCO test-dev
AP50· uses extra data· 2025-05-23
91.9
best: 95 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
3DonCOCO test-dev
AP75· uses extra data· 2025-05-23
85.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
3DonCOCO test-dev
APM· uses extra data· 2025-05-23
75.9
best: 83.8 (4xRSN-50 (ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
3DonCOCO test-dev
AR· uses extra data· 2025-05-23
84.5
best: 88.2 (Simple Pose)
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475

Audio8 results

1 Image, 2*2 StitchionCOCO test-dev
APL· uses extra data· 2025-05-23
86.5
SOTA
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
1 Image, 2*2 StitchionOCHuman
Test AP· uses extra data· 2025-05-23
87
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
1 Image, 2*2 StitchionOCHuman
Validation AP· uses extra data· 2025-05-23
86
best: 92.8 (ViTPose (ViTAE-G, GT bounding boxes))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
1 Image, 2*2 StitchionCOCO test-dev
AP· uses extra data· 2025-05-23
79.5
best: 81.1 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
1 Image, 2*2 StitchionCOCO test-dev
AP50· uses extra data· 2025-05-23
91.9
best: 95 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
1 Image, 2*2 StitchionCOCO test-dev
AP75· uses extra data· 2025-05-23
85.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
1 Image, 2*2 StitchionCOCO test-dev
APM· uses extra data· 2025-05-23
75.9
best: 83.8 (4xRSN-50 (ensemble))
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475
1 Image, 2*2 StitchionCOCO test-dev
AR· uses extra data· 2025-05-23
84.5
best: 88.2 (Simple Pose)
PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation arXiv:2505.17475