| Benchmark | Model | Rank | Results |
|---|---|---|---|
| action-segmentation-on-coin | Univl | #2 | Frame accuracy: 70.0 |
| video-captioning-on-youcook2 | UniVL | #3 | BLEU-4: 17.35BLEU-3: 23.87CIDEr: 1.81ROUGE-L: 46.52… |
| video-retrieval-on-msr-vtt | UniVL | #24 | text-to-video R@1: 21.2text-to-video R@5: 49.6… |
| video-retrieval-on-youcook2 | UniVL | #4 | text-to-video R@1: 28.9text-to-video R@5: 57.6… |