| video-captioning-on-msr-vtt-1 | VIOLETv2 | #11 | CIDEr: 58 |
| video-captioning-on-msvd-1 | VIOLETv2 | #7 | CIDEr: 139.2 |
| video-question-answering-on-msrvtt-mc | VIOLETv2 | #1 | Accuracy: 97.6 |
| video-question-answering-on-msrvtt-qa | VIOLETv2 | #10 | Accuracy: 44.5 |
| video-retrieval-on-didemo | VIOLETv2 | #22 | text-to-video R@1: 47.9text-to-video R@5: 76.5… |
| video-retrieval-on-lsmdc | VIOLETv2 | #17 | text-to-video R@1: 24text-to-video R@5: 43.5text-to-video R@10: 54.1 |
| video-retrieval-on-msr-vtt | VIOLETv2 | #12 | text-to-video R@1: 37.2text-to-video R@5: 64.8… |
| visual-question-answering-on-msvd-qa-1 | VIOLETv2 | #12 | Accuracy: 0.547 |