UniHCP (direct eval)

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 EstimationonOCHuman
Test AP· 2023-03-06
87.4
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
UniHCP: A Unified Model for Human-Centric Perceptions arXiv:2303.02936

Methodology1 result

3DonOCHuman
Test AP· 2023-03-06
87.4
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
UniHCP: A Unified Model for Human-Centric Perceptions arXiv:2303.02936

Audio1 result

1 Image, 2*2 StitchionOCHuman
Test AP· 2023-03-06
87.4
best: 93.3 (ViTPose (ViTAE-G, GT bounding boxes))
UniHCP: A Unified Model for Human-Centric Perceptions arXiv:2303.02936