| video-retrieval-on-activitynet | vid-TLDR (UMT-L) | #7 | text-to-video R@1: 66.7text-to-video R@5: 88.6… |
| video-retrieval-on-didemo | vid-TLDR (UMT-L) | #2 | text-to-video R@1: 72.3text-to-video R@5: 91.2… |
| video-retrieval-on-lsmdc | vid-TLDR (UMT-L) | #2 | text-to-video R@1: 43.1text-to-video R@5: 64.5… |
| video-retrieval-on-msr-vtt | vid-TLDR (UMT-L) | #6 | text-to-video R@1: 58.1text-to-video R@5: 81.0… |
| video-retrieval-on-msvd | vid-TLDR (UMT-L) | #3 | text-to-video R@1: 57.9text-to-video R@5: 83.8… |
| video-retrieval-on-ssv2-label-retrieval | vid-TLDR (UMT-L) | #2 | text-to-video R@1: 73.1text-to-video R@5: 93.3… |
| video-retrieval-on-ssv2-template-retrieval | vid-TLDR (UMT-L) | #2 | text-to-video R@1: 90.2text-to-video R@10: 100.0… |
| visual-question-answering-on-msrvtt-qa-1 | vid-TLDR (UMT-L) | #7 | Accuracy: 0.470 |
| visual-question-answering-on-msvd-qa-1 | vid-TLDR (UMT-L) | #11 | Accuracy: 0.549 |
| zero-shot-video-retrieval-on-activitynet | vid-TLDR (UMT-L) | #5 | text-to-video R@1: 42.8text-to-video R@5: 69.4… |
| zero-shot-video-retrieval-on-didemo | vid-TLDR (UMT-L) | #5 | text-to-video R@1: 52.0text-to-video R@5: 74.0… |
| zero-shot-video-retrieval-on-msr-vtt | vid-TLDR (UMT-L) | #12 | text-to-video R@1: 42.1text-to-video R@5: 63.9… |
| zero-shot-video-retrieval-on-msvd | vid-TLDR (UMT-L) | #6 | text-to-video R@1: 50.0text-to-video R@5: 77.6… |