| Paper | Code | KLD | Top-1 Action Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Affordance Grounding from Demonstration Video to Target Image | ✓ Link | 1.51 | 52.27 | Afformer (ViTDet-B encoder) | 2023-03-26 |
| Affordance Grounding from Demonstration Video to Target Image | ✓ Link | 1.55 | 52.14 | Afformer (ResNet-50-FPN encoder) | 2023-03-26 |
| Demo2Vec: Reasoning Object Affordances From Online Videos | 2.34 | 40.79 | Demo2Vec | 2018-06-01 |