PEFORMER-Xcit-dino-p8

Reported on 6 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 Vision2 results

Pose EstimationonCOCO (Common Objects in Context)
AP· 2021-12-09
72.6
best: 79.5 (OmniPose (WASPv2))
PE-former: Pose Estimation Transformer arXiv:2112.04981
Pose EstimationonCOCO (Common Objects in Context)
AR· 2021-12-09
79.4
best: 82.1 (I²R-Net (1st stage:HRFormer-B))
PE-former: Pose Estimation Transformer arXiv:2112.04981

Methodology2 results

3DonCOCO (Common Objects in Context)
AP· 2021-12-09
72.6
best: 79.5 (OmniPose (WASPv2))
PE-former: Pose Estimation Transformer arXiv:2112.04981
3DonCOCO (Common Objects in Context)
AR· 2021-12-09
79.4
best: 82.1 (I²R-Net (1st stage:HRFormer-B))
PE-former: Pose Estimation Transformer arXiv:2112.04981

Audio2 results

1 Image, 2*2 StitchionCOCO (Common Objects in Context)
AP· 2021-12-09
72.6
best: 79.5 (OmniPose (WASPv2))
PE-former: Pose Estimation Transformer arXiv:2112.04981
1 Image, 2*2 StitchionCOCO (Common Objects in Context)
AR· 2021-12-09
79.4
best: 82.1 (I²R-Net (1st stage:HRFormer-B))
PE-former: Pose Estimation Transformer arXiv:2112.04981