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/HigherHRNet (HR-Net-48)

HigherHRNet (HR-Net-48)

Reported on 20 benchmarks across 4 tasks · 1 paper · 5 SOTA

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

Computer Vision10 results

Multi-Person Pose EstimationonCOCO test-dev
AP· 2019-08-27
70.5
best: 79.2 (SCIO (HRNet-48))
SOTA
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Multi-Person Pose EstimationonCOCO test-dev
AP50· 2019-08-27
89.3
best: 93.5 (SCIO (HRNet-48))
SOTA
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Multi-Person Pose EstimationonCOCO test-dev
AP75· 2019-08-27
77.2
best: 85.8 (SCIO (HRNet-48))
SOTA
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Multi-Person Pose EstimationonCOCO test-dev
APL· 2019-08-27
75.8
best: 84.2 (SCIO (HRNet-48))
SOTA
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Multi-Person Pose EstimationonCOCO test-dev
APM· 2019-08-27
66.6
best: 74.1 (SCIO (HRNet-48))
SOTA
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Pose EstimationonCOCO test-dev
AP· 2019-08-27
70.5
best: 81.1 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Pose EstimationonCOCO test-dev
AP50· 2019-08-27
89.3
best: 95 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Pose EstimationonCOCO test-dev
AP75· 2019-08-27
77.2
best: 88.2 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Pose EstimationonCOCO test-dev
APL· 2019-08-27
75.8
best: 86.5 (PoseBH-H)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
Pose EstimationonCOCO test-dev
APM· 2019-08-27
66.6
best: 83.8 (4xRSN-50 (ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357

Methodology5 results

3DonCOCO test-dev
AP· 2019-08-27
70.5
best: 81.1 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
3DonCOCO test-dev
AP50· 2019-08-27
89.3
best: 95 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
3DonCOCO test-dev
AP75· 2019-08-27
77.2
best: 88.2 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
3DonCOCO test-dev
APL· 2019-08-27
75.8
best: 86.5 (PoseBH-H)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
3DonCOCO test-dev
APM· 2019-08-27
66.6
best: 83.8 (4xRSN-50 (ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357

Audio5 results

1 Image, 2*2 StitchionCOCO test-dev
AP· 2019-08-27
70.5
best: 81.1 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
1 Image, 2*2 StitchionCOCO test-dev
AP50· 2019-08-27
89.3
best: 95 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
1 Image, 2*2 StitchionCOCO test-dev
AP75· 2019-08-27
77.2
best: 88.2 (ViTPose (ViTAE-G, ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
1 Image, 2*2 StitchionCOCO test-dev
APL· 2019-08-27
75.8
best: 86.5 (PoseBH-H)
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357
1 Image, 2*2 StitchionCOCO test-dev
APM· 2019-08-27
66.6
best: 83.8 (4xRSN-50 (ensemble))
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation arXiv:1908.10357