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/Identity Mapping Hourglass

Identity Mapping Hourglass

Reported on 20 benchmarks across 4 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 Vision10 results

Multi-Person Pose EstimationonCOCO test-dev
APM· 2019-11-24
66.8
best: 74.1 (SCIO (HRNet-48))
SOTA
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Multi-Person Pose EstimationonCOCO test-dev
AR· 2019-11-24
72.1
best: 81.6 (SCIO (HRNet-48))
SOTA
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Multi-Person Pose EstimationonCOCO test-dev
AR50· 2019-11-24
88.2
best: 92.3 (HigherHRNet (ScaleNet_P4))
SOTA
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Pose EstimationonCOCO test-dev
AP· 2019-11-24
68.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Pose EstimationonCOCO test-dev
APL· 2019-11-24
70.5
best: 86.5 (PoseBH-H)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Pose EstimationonCOCO test-dev
APM· 2019-11-24
66.8
best: 83.8 (4xRSN-50 (ensemble))
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Pose EstimationonCOCO test-dev
AR· 2019-11-24
72.1
best: 88.2 (Simple Pose)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Pose EstimationonCOCO test-dev
AR50· 2019-11-24
88.2
best: 96.3 (MSPN)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Multi-Person Pose EstimationonCOCO test-dev
AP· 2019-11-24
68.1
best: 79.2 (SCIO (HRNet-48))
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
Multi-Person Pose EstimationonCOCO test-dev
APL· 2019-11-24
70.5
best: 84.2 (SCIO (HRNet-48))
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529

Methodology5 results

3DonCOCO test-dev
AP· 2019-11-24
68.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
3DonCOCO test-dev
APL· 2019-11-24
70.5
best: 86.5 (PoseBH-H)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
3DonCOCO test-dev
APM· 2019-11-24
66.8
best: 83.8 (4xRSN-50 (ensemble))
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
3DonCOCO test-dev
AR· 2019-11-24
72.1
best: 88.2 (Simple Pose)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
3DonCOCO test-dev
AR50· 2019-11-24
88.2
best: 96.3 (MSPN)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529

Audio5 results

1 Image, 2*2 StitchionCOCO test-dev
AP· 2019-11-24
68.1
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
1 Image, 2*2 StitchionCOCO test-dev
APL· 2019-11-24
70.5
best: 86.5 (PoseBH-H)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
1 Image, 2*2 StitchionCOCO test-dev
APM· 2019-11-24
66.8
best: 83.8 (4xRSN-50 (ensemble))
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
1 Image, 2*2 StitchionCOCO test-dev
AR· 2019-11-24
72.1
best: 88.2 (Simple Pose)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529
1 Image, 2*2 StitchionCOCO test-dev
AR50· 2019-11-24
88.2
best: 96.3 (MSPN)
Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation arXiv:1911.10529