Online Product Reviews for Affordances
The OPRA Dataset was introduced in Demo2Vec: Reasoning Object Affordances From Online Videos (CVPR'18) for reasoning object affordances from online demonstration videos. It contains 11,505 demonstration clips and 2,512 object images scraped from 6 popular YouTube product review channels along with the corresponding affordance annotations. More details can be found on our https://sites.google.com/view/demo2vec/.
Variants: OPRA, OPRA (28x28)
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Video-to-image Affordance Grounding | Afformer (ViTDet-B encoder) | Affordance Grounding from Demonstration Video … | 2023-03-26 |
| Video-to-image Affordance Grounding | Afformer (ResNet-50-FPN encoder) | Affordance Grounding from Demonstration Video … | 2023-03-26 |
Recent papers with results on this dataset: