| visual-question-answering-on-msrvtt-qa | FrozenBiLM+ | #7 | Accuracy: 0.470 |
| visual-question-answering-on-msrvtt-qa | JustAsk+ | #20 | Accuracy: 0.418 |
| visual-question-answering-on-msrvtt-qa | All-in-one+ | #21 | Accuracy: 0.395 |
| visual-question-answering-on-msvd-qa | FrozenBiLM+ | #8 | Accuracy: 0.558 |
| visual-question-answering-on-msvd-qa | VIOLET+ | #17 | Accuracy: 0.495 |
| visual-question-answering-on-msvd-qa | JustAsk+ | #20 | Accuracy: 0.477 |
| visual-question-answering-on-msvd-qa | All-in-one+ | #24 | Accuracy: 0.438 |
| video-question-answering-on-activitynet-qa | FrozenBiLM+ | #14 | Accuracy: 44.8 |
| video-question-answering-on-activitynet-qa | All-in-one+ | #20 | Accuracy: 40.0 |
| video-question-answering-on-activitynet-qa | VIOLET+ | #21 | Accuracy: 39.7 |