| video-question-answering-on-activitynet-qa | Singularity-temporal | #16 | Accuracy: 44.1 |
| video-question-answering-on-activitynet-qa | Singularity | #18 | Accuracy: 43.1 |
| video-question-answering-on-msrvtt-mc | Singularity-temporal | #4 | Accuracy: 93.7 |
| video-question-answering-on-msrvtt-mc | Singularity | #6 | Accuracy: 92.1 |
| video-question-answering-on-msrvtt-qa | Singularity-temporal | #11 | Accuracy: 43.9 |
| video-question-answering-on-msrvtt-qa | Singularity | #12 | Accuracy: 43.5 |
| video-retrieval-on-activitynet | Singularity | #17 | text-to-video R@1: 47.1text-to-video R@5: 75.5… |
| video-retrieval-on-didemo | Singularity | #15 | text-to-video R@1: 53.9text-to-video R@5: 79.4… |
| video-retrieval-on-msr-vtt-1ka | Singularity | #31 | text-to-video R@1: 41.5text-to-video R@5: 68.7text-to-video R@10: 77 |
| video-retrieval-on-ssv2-label-retrieval | Singularity-temporal | #4 | text-to-video R@1: 47.4text-to-video R@5: 75.9text-to-video R@10: 84 |
| video-retrieval-on-ssv2-template-retrieval | Singularity-temporal | #4 | text-to-video R@1: 77.6text-to-video R@10: 98.9text-to-video R@5: 96 |
| zero-shot-video-retrieval-on-activitynet | Singularity-temporal-5M | #9 | text-to-video R@1: 30.8text-to-video R@5: 55.9… |
| zero-shot-video-retrieval-on-activitynet | Singularity-temporal-17M | #11 | text-to-video R@1: 30.6text-to-video R@5: 55.6… |
| zero-shot-video-retrieval-on-didemo | Singularity-17M | #10 | text-to-video R@1: 37.1text-to-video R@5: 61.7… |
| zero-shot-video-retrieval-on-didemo | Singularity-5M | #11 | text-to-video R@1: 36.9text-to-video R@5: 61.1… |
| zero-shot-video-retrieval-on-msr-vtt | Singularity-17M | #18 | text-to-video R@1: 34.0text-to-video R@5: 56.7… |
| zero-shot-video-retrieval-on-msr-vtt | Singularity-5M | #21 | text-to-video R@1: 28.4text-to-video R@5: 50.2… |