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/PersonLab

PersonLab

Reported on 23 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 Vision11 results

Multi-Person Pose EstimationonCOCO test-dev
AP· 2018-03-22
68.7
best: 79.2 (SCIO (HRNet-48))
SOTA
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Multi-Person Pose EstimationonCOCO test-dev
AP50· 2018-03-22
89
best: 93.5 (SCIO (HRNet-48))
SOTA
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Multi-Person Pose EstimationonCOCO test-dev
AP75· 2018-03-22
75.4
best: 85.8 (SCIO (HRNet-48))
SOTA
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Multi-Person Pose EstimationonCOCO test-dev
APL· 2018-03-22
75.5
best: 84.2 (SCIO (HRNet-48))
SOTA
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Multi-Person Pose EstimationonCOCO test-dev
APM· 2018-03-22
64.1
best: 74.1 (SCIO (HRNet-48))
SOTA
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Pose EstimationonCOCO (Common Objects in Context)
Test AP· 2018-03-22
66.5
best: 78.6 (4xRSN-50(384×288))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Pose EstimationonCOCO test-dev
AP· 2018-03-22
68.7
best: 81.1 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Pose EstimationonCOCO test-dev
AP50· 2018-03-22
89
best: 95 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Pose EstimationonCOCO test-dev
AP75· 2018-03-22
75.4
best: 88.2 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Pose EstimationonCOCO test-dev
APL· 2018-03-22
75.5
best: 86.5 (PoseBH-H)
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
Pose EstimationonCOCO test-dev
APM· 2018-03-22
64.1
best: 83.8 (4xRSN-50 (ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225

Methodology6 results

3DonCOCO (Common Objects in Context)
Test AP· 2018-03-22
66.5
best: 78.6 (4xRSN-50(384×288))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
3DonCOCO test-dev
AP· 2018-03-22
68.7
best: 81.1 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
3DonCOCO test-dev
AP50· 2018-03-22
89
best: 95 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
3DonCOCO test-dev
AP75· 2018-03-22
75.4
best: 88.2 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
3DonCOCO test-dev
APL· 2018-03-22
75.5
best: 86.5 (PoseBH-H)
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
3DonCOCO test-dev
APM· 2018-03-22
64.1
best: 83.8 (4xRSN-50 (ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225

Audio6 results

1 Image, 2*2 StitchionCOCO (Common Objects in Context)
Test AP· 2018-03-22
66.5
best: 78.6 (4xRSN-50(384×288))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
1 Image, 2*2 StitchionCOCO test-dev
AP· 2018-03-22
68.7
best: 81.1 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
1 Image, 2*2 StitchionCOCO test-dev
AP50· 2018-03-22
89
best: 95 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
1 Image, 2*2 StitchionCOCO test-dev
AP75· 2018-03-22
75.4
best: 88.2 (ViTPose (ViTAE-G, ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
1 Image, 2*2 StitchionCOCO test-dev
APL· 2018-03-22
75.5
best: 86.5 (PoseBH-H)
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225
1 Image, 2*2 StitchionCOCO test-dev
APM· 2018-03-22
64.1
best: 83.8 (4xRSN-50 (ensemble))
PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model arXiv:1803.08225