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/PCT (256x256)

PCT (256x256)

Reported on 9 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 Vision3 results

Pose EstimationonCOCO test-dev
AP· 2023-03-21
78.3
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638
Pose EstimationonCOCO test-dev
AP50· 2023-03-21
9
best: 95 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638
Pose EstimationonCOCO test-dev
AP75· 2023-03-21
85.9
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638

Methodology3 results

3DonCOCO test-dev
AP· 2023-03-21
78.3
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638
3DonCOCO test-dev
AP50· 2023-03-21
9
best: 95 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638
3DonCOCO test-dev
AP75· 2023-03-21
85.9
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638

Audio3 results

1 Image, 2*2 StitchionCOCO test-dev
AP· 2023-03-21
78.3
best: 81.1 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638
1 Image, 2*2 StitchionCOCO test-dev
AP50· 2023-03-21
9
best: 95 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638
1 Image, 2*2 StitchionCOCO test-dev
AP75· 2023-03-21
85.9
best: 88.2 (ViTPose (ViTAE-G, ensemble))
Human Pose as Compositional Tokens arXiv:2303.11638