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/HRNet-W48 + extra data

HRNet-W48 + extra data

Reported on 18 benchmarks across 3 tasks · 1 paper · 15 SOTA

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

Computer Vision6 results

Pose EstimationonCOCO test-dev
AP· 2019-02-25
77
best: 81.1 (ViTPose (ViTAE-G, ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
Pose EstimationonCOCO test-dev
AP75· 2019-02-25
84.5
best: 88.2 (ViTPose (ViTAE-G, ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
Pose EstimationonCOCO test-dev
APL· 2019-02-25
83.1
best: 86.5 (PoseBH-H)
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
Pose EstimationonCOCO test-dev
APM· 2019-02-25
73.4
best: 83.8 (4xRSN-50 (ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
Pose EstimationonCOCO test-dev
AR· 2019-02-25
82
best: 88.2 (Simple Pose)
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
Pose EstimationonCOCO test-dev
AP50· 2019-02-25
92.7
best: 95 (ViTPose (ViTAE-G, ensemble))
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212

Methodology6 results

3DonCOCO test-dev
AP· 2019-02-25
77
best: 81.1 (ViTPose (ViTAE-G, ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
3DonCOCO test-dev
AP75· 2019-02-25
84.5
best: 88.2 (ViTPose (ViTAE-G, ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
3DonCOCO test-dev
APL· 2019-02-25
83.1
best: 86.5 (PoseBH-H)
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
3DonCOCO test-dev
APM· 2019-02-25
73.4
best: 83.8 (4xRSN-50 (ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
3DonCOCO test-dev
AR· 2019-02-25
82
best: 88.2 (Simple Pose)
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
3DonCOCO test-dev
AP50· 2019-02-25
92.7
best: 95 (ViTPose (ViTAE-G, ensemble))
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212

Audio6 results

1 Image, 2*2 StitchionCOCO test-dev
AP· 2019-02-25
77
best: 81.1 (ViTPose (ViTAE-G, ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
1 Image, 2*2 StitchionCOCO test-dev
AP75· 2019-02-25
84.5
best: 88.2 (ViTPose (ViTAE-G, ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
1 Image, 2*2 StitchionCOCO test-dev
APL· 2019-02-25
83.1
best: 86.5 (PoseBH-H)
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
1 Image, 2*2 StitchionCOCO test-dev
APM· 2019-02-25
73.4
best: 83.8 (4xRSN-50 (ensemble))
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
1 Image, 2*2 StitchionCOCO test-dev
AR· 2019-02-25
82
best: 88.2 (Simple Pose)
SOTA
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212
1 Image, 2*2 StitchionCOCO test-dev
AP50· 2019-02-25
92.7
best: 95 (ViTPose (ViTAE-G, ensemble))
Deep High-Resolution Representation Learning for Human Pose Estimation arXiv:1902.09212