Video To Image Affordance Grounding On Epic
評価指標
AUC-J
KLD
SIM
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | AUC-J | KLD | SIM | Paper Title | Repository |
|---|---|---|---|---|---|
| Afformer | 0.88 | 0.97 | 0.56 | Affordance Grounding from Demonstration Video to Target Image | |
| HAG-Net (+Hand Box) | 0.80 | 1.21 | 0.41 | Learning Visual Affordance Grounding from Demonstration Videos | - |
| Hotspot | 0.79 | 1.26 | 0.40 | Grounded Human-Object Interaction Hotspots from Video |
0 of 3 row(s) selected.