| video-retrieval-on-msvd | SSML | #19 | text-to-video R@1: 20.3text-to-video R@5: 49.0… |
| visual-question-answering-on-msrvtt-qa-2 | SSML | #3 | Accuracy: 0.35 |
| visual-question-answering-on-msvd-qa-1 | SSML | #27 | Accuracy: 0.351 |
| zero-shot-video-retrieval-on-lsmdc | SSML | #14 | text-to-video R@1: 4.2text-to-video R@5: 11.6text-to-video R@10: 17.1 |
| zero-shot-video-retrieval-on-msr-vtt | SSML | #33 | text-to-video R@1: 8.0text-to-video R@5: 21.3text-to-video R@10: 29.3 |
| zero-shot-video-retrieval-on-msvd | SSML | #13 | text-to-video R@1: 13.66text-to-video R@5: 35.7… |