BUCTD-W48 (w/cond. input from PETR)

Reported on 3 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 Vision1 result

Pose EstimationonCrowdPose
AP· 2023-06-13
76.7
best: 78.5 (BUCTD-W48 (w/cond. input from PETR, and generative sampling))
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity arXiv:2306.07879

Methodology1 result

3DonCrowdPose
AP· 2023-06-13
76.7
best: 78.5 (BUCTD-W48 (w/cond. input from PETR, and generative sampling))
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity arXiv:2306.07879

Audio1 result

1 Image, 2*2 StitchionCrowdPose
AP· 2023-06-13
76.7
best: 78.5 (BUCTD-W48 (w/cond. input from PETR, and generative sampling))
Rethinking pose estimation in crowds: overcoming the detection information-bottleneck and ambiguity arXiv:2306.07879