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/MSPN

MSPN

Reported on 36 benchmarks across 3 tasks · 1 paper · 21 SOTA

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

Computer Vision18 results

Pose EstimationonCOCO minival
AP· 2019-01-01
75.9
best: 79.1 (HRNet-W48plus)
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AP· 2019-01-01
76.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AP50· 2019-01-01
93.4
best: 95 (ViTPose (ViTAE-G, ensemble))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AR· 2019-01-01
81.6
best: 88.2 (Simple Pose)
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonMPII Human Pose
PCKh-0.5· 2019-01-01
92.6
best: 94.3 (PCT (swin-l, test set))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AR50· 2019-01-01
96.3
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
ARM· 2019-01-01
77.5
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AP75· 2019-01-01
83.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
APL· 2019-01-01
81.5
best: 86.5 (PoseBH-H)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
APM· 2019-01-01
72.3
best: 83.8 (4xRSN-50 (ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AP· 2019-01-01
76.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AP50· 2019-01-01
93.4
best: 95 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AP75· 2019-01-01
83.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
APL· 2019-01-01
81.5
best: 86.5 (PoseBH-H)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
APM· 2019-01-01
72.3
best: 83.8 (4xRSN-50 (ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AR· 2019-01-01
81.6
best: 88.2 (Simple Pose)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
AR75· 2019-01-01
88.1
best: 88.2 (Simple Base+*)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
Pose EstimationonCOCO test-dev
ARL· 2019-01-01
87.1
best: 87.2 (Simple Base+*)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148

Methodology18 results

3DonCOCO minival
AP· 2019-01-01
75.9
best: 79.1 (HRNet-W48plus)
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AP· 2019-01-01
76.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AP50· 2019-01-01
93.4
best: 95 (ViTPose (ViTAE-G, ensemble))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AR· 2019-01-01
81.6
best: 88.2 (Simple Pose)
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonMPII Human Pose
PCKh-0.5· 2019-01-01
92.6
best: 94.3 (PCT (swin-l, test set))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AR50· 2019-01-01
96.3
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
ARM· 2019-01-01
77.5
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AP75· 2019-01-01
83.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
APL· 2019-01-01
81.5
best: 86.5 (PoseBH-H)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
APM· 2019-01-01
72.3
best: 83.8 (4xRSN-50 (ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AP· 2019-01-01
76.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AP50· 2019-01-01
93.4
best: 95 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AP75· 2019-01-01
83.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
APL· 2019-01-01
81.5
best: 86.5 (PoseBH-H)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
APM· 2019-01-01
72.3
best: 83.8 (4xRSN-50 (ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AR· 2019-01-01
81.6
best: 88.2 (Simple Pose)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
AR75· 2019-01-01
88.1
best: 88.2 (Simple Base+*)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
3DonCOCO test-dev
ARL· 2019-01-01
87.1
best: 87.2 (Simple Base+*)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148

Audio18 results

1 Image, 2*2 StitchionCOCO minival
AP· 2019-01-01
75.9
best: 79.1 (HRNet-W48plus)
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AP· 2019-01-01
76.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AP50· 2019-01-01
93.4
best: 95 (ViTPose (ViTAE-G, ensemble))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AR· 2019-01-01
81.6
best: 88.2 (Simple Pose)
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionMPII Human Pose
PCKh-0.5· 2019-01-01
92.6
best: 94.3 (PCT (swin-l, test set))
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AR50· 2019-01-01
96.3
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
ARM· 2019-01-01
77.5
SOTA
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AP75· 2019-01-01
83.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
APL· 2019-01-01
81.5
best: 86.5 (PoseBH-H)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
APM· 2019-01-01
72.3
best: 83.8 (4xRSN-50 (ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AP· 2019-01-01
76.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AP50· 2019-01-01
93.4
best: 95 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AP75· 2019-01-01
83.8
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
APL· 2019-01-01
81.5
best: 86.5 (PoseBH-H)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
APM· 2019-01-01
72.3
best: 83.8 (4xRSN-50 (ensemble))
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AR· 2019-01-01
81.6
best: 88.2 (Simple Pose)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
AR75· 2019-01-01
88.1
best: 88.2 (Simple Base+*)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148
1 Image, 2*2 StitchionCOCO test-dev
ARL· 2019-01-01
87.1
best: 87.2 (Simple Base+*)
Rethinking on Multi-Stage Networks for Human Pose Estimation arXiv:1901.00148