From Grounded Human-Object Interaction Hotspots from Video (ICCV'19): We collect annotations for interaction keypoints on EPIC Kitchens in order to quantitatively evaluate our method in parallel to the OPRA dataset (where annotations are available). We note that these annotations are collected purely for evaluation, and are not used for training our model. We select the 20 most frequent verbs, and select 31 nouns that afford these interactions.
Variants: EPIC-Hotspot
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Video-to-image Affordance Grounding | Afformer | Affordance Grounding from Demonstration Video … | 2023-03-26 |
| Video-to-image Affordance Grounding | HAG-Net (+Hand Box) | Learning Visual Affordance Grounding from … | 2021-08-12 |
| Video-to-image Affordance Grounding | Hotspot | Grounded Human-Object Interaction Hotspots from … | 2018-12-11 |
Recent papers with results on this dataset: