LOGO-CAP (Ours) HRNet-W48

Reported on 6 benchmarks across 3 tasks

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

Computer Vision2 results

Pose EstimationonCOCO 2017 val
AP
72.2
Pose EstimationonCOCO test-dev
AP
70.8
best: 81.1 (ViTPose (ViTAE-G, ensemble))

Methodology2 results

3DonCOCO 2017 val
AP
72.2
3DonCOCO test-dev
AP
70.8
best: 81.1 (ViTPose (ViTAE-G, ensemble))

Audio2 results

1 Image, 2*2 StitchionCOCO 2017 val
AP
72.2
1 Image, 2*2 StitchionCOCO test-dev
AP
70.8
best: 81.1 (ViTPose (ViTAE-G, ensemble))