Video To Image Affordance Grounding On Opra 1
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 |
|---|---|---|---|---|---|
| Hotspot | 0.81 | 1.47 | 0.36 | Grounded Human-Object Interaction Hotspots from Video | |
| HAG-Net (+Hand Box) | 0.81 | 1.41 | 0.37 | Learning Visual Affordance Grounding from Demonstration Videos | - |
| Demo2Vec | 0.85 | 1.20 | 0.48 | Demo2Vec: Reasoning Object Affordances From Online Videos | - |
| Afformer | 0.89 | 1.05 | 0.53 | Affordance Grounding from Demonstration Video to Target Image |
0 of 4 row(s) selected.