ViTPose-h

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Knowledge Base2 results

2D Human Pose EstimationonHuman-Art
AP· 2022-04-26
0.468
best: 0.759 (UniPose)
SOTA
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484
2D Human Pose EstimationonHuman-Art
AP (gt bbox)· 2022-04-26
0.8
SOTA
ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation arXiv:2204.12484