| science-question-answering-on-scienceqa | Video-LaVIT | #9 | Avg. Accuracy: 70.0 |
| text-to-video-generation-on-msr-vtt | Video-LaVIT | #1 | FVD: 188.36CLIPSIM: 0.3012FID: 11.27 |
| video-generation-on-ucf-101 | Video-LaVIT | #16 | FVD16: 280.57Inception Score: 44.26 |
| visual-question-answering-on-gqa-test-dev | Video-LaVIT | #3 | Accuracy: 64.4 |
| visual-question-answering-on-mm-vet | Video-LaVIT | #122 | GPT-4 score: 33.2Params: 7B |
| visual-question-answering-on-mmbench | Video-LaVIT | #4 | GPT-3.5 score: 67.3 |
| visual-question-answering-on-vizwiz-2020-vqa | Video-LaVIT | #2 | overall: 56.0 |
| zeroshot-video-question-answer-on-activitynet | Video-LaVIT | #13 | Accuracy: 50.1Confidence Score: 3.3 |
| zeroshot-video-question-answer-on-msrvtt-qa | Video-LaVIT | #15 | Accuracy: 59.3Confidence Score: 3.3 |
| zeroshot-video-question-answer-on-msvd-qa | Video-LaVIT | #14 | Accuracy: 73.2Confidence Score: 3.9 |