VidOR
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Relation Tagging | VidOR (val) | P@555.16 | 14 | |
| Relation Tagging | VidOR SOTA comparisons (val) | P@168.86 | 14 | |
| Relation Detection | VidOR SOTA comparisons (val) | mAP11.21 | 14 | |
| Visual Relation Detection | VidOR (val) | R@500.0999 | 13 | |
| Video Question Answering | VidOR | VQA Accuracy79 | 3 | |
| Video Scene Graph Generation | VidOR | Entity Accuracy93.1 | 2 |
Showing 6 of 6 rows