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/PPE (ResNeXt-101)

PPE (ResNeXt-101)

Reported on 15 benchmarks across 3 tasks · 1 paper

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

Computer Vision5 results

Pose EstimationonCOCO test-dev
AP· 2022-06-15
75.7
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
Pose EstimationonCOCO test-dev
AP50· 2022-06-15
90.3
best: 95 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
Pose EstimationonCOCO test-dev
AP75· 2022-06-15
76.3
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
Pose EstimationonCOCO test-dev
APL· 2022-06-15
79.5
best: 86.5 (PoseBH-H)
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
Pose EstimationonCOCO test-dev
APM· 2022-06-15
80.7
best: 83.8 (4xRSN-50 (ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510

Methodology5 results

3DonCOCO test-dev
AP· 2022-06-15
75.7
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
3DonCOCO test-dev
AP50· 2022-06-15
90.3
best: 95 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
3DonCOCO test-dev
AP75· 2022-06-15
76.3
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
3DonCOCO test-dev
APL· 2022-06-15
79.5
best: 86.5 (PoseBH-H)
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
3DonCOCO test-dev
APM· 2022-06-15
80.7
best: 83.8 (4xRSN-50 (ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510

Audio5 results

1 Image, 2*2 StitchionCOCO test-dev
AP· 2022-06-15
75.7
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
1 Image, 2*2 StitchionCOCO test-dev
AP50· 2022-06-15
90.3
best: 95 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
1 Image, 2*2 StitchionCOCO test-dev
AP75· 2022-06-15
76.3
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
1 Image, 2*2 StitchionCOCO test-dev
APL· 2022-06-15
79.5
best: 86.5 (PoseBH-H)
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510
1 Image, 2*2 StitchionCOCO test-dev
APM· 2022-06-15
80.7
best: 83.8 (4xRSN-50 (ensemble))
Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation arXiv:2206.07510