Human Part Segmentation On Human3 6M
평가 지표
mIoU
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | mIoU | Paper Title | Repository |
|---|---|---|---|
| Hulk(Finetune, ViT-L) | 69.89 | Hulk: A Universal Knowledge Translator for Human-Centric Tasks | |
| UniHCP (finetune) | 65.95 | UniHCP: A Unified Model for Human-Centric Perceptions | |
| Hulk(Finetune, ViT-B) | 68.56 | Hulk: A Universal Knowledge Translator for Human-Centric Tasks |
0 of 3 row(s) selected.