| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Video Chaptering | VidChapters-7M (test) | F1 Score45.3 | 8 | |
| Video Chaptering | VidChapters-7M Long (test) | F1 Score41.3 | 8 | |
| Video Chaptering | VidChapters-7M Medium (test) | F1 Score46.7 | 8 | |
| Video Chaptering | VidChapters-7M Short (test) | F1 Score45.5 | 8 | |
| Embedding Similarity | VidChapters7M | Cosine Similarity6.45 | 6 | |
| Temporal Grounding | VidChapters-7M (test) | R1@0.33,740 | 5 | |
| Visual Explanation Generation | VidChapters7M (test) | FVD105 | 3 | |
| Feature Visualization | VidChapters7M | FVD142 | 3 | |
| Video chapter generation | VidChapters (test) | Precision @ 5s52 | 2 |