Video-to-image Affordance Grounding 벤치마크
Video-to-image Affordance Grounding on OPRA (28x28)
KLD
- 2018-06-01 — Demo2Vec: KLD 1.2
- 2018-12-11 — Hotspot: KLD 1.47
| Rank | Model | KLD | SIM | AUC-J | Paper | Code | Year |
|---|---|---|---|---|---|---|---|
| 1 | Afformer | 1.05 | 0.53 | 0.89 | Affordance Grounding from Demonstration Video to Target Image | showlab/afformer | 2023 |
| 2 | Demo2Vec | 1.20 | 0.48 | 0.85 | Demo2Vec: Reasoning Object Affordances From Online Videos | 2018 | |
| 3 | HAG-Net (+Hand Box) | 1.41 | 0.37 | 0.81 | Learning Visual Affordance Grounding from Demonstration Videos | 2021 | |
| 4 | Hotspot | 1.47 | 0.36 | 0.81 | Grounded Human-Object Interaction Hotspots from Video | Tushar-N/interaction-hotspots | 2018 |