| highlight-detection-on-qvhighlights | VideoChat-T (FT) | #19 | mAP: 27.0Hit@1: 55.3 |
| moment-retrieval-on-charades-sta | VideoChat-T (FT) | #7 | R@1 IoU=0.5: 67.1R@1 IoU=0.7: 43.0 |
| moment-retrieval-on-charades-sta | VideoChat-T (ZS) | #23 | R@1 IoU=0.5: 48.7R@1 IoU=0.7: 24.0mIoU: 45.43 |
| video-question-answering-on-mvbench | VideoChat-T (7B) | #7 | Avg.: 59.9 |
| zero-shot-video-question-answer-on-egoschema | VideoChat-T (7B) | #2 | Accuracy: 68.4 |
| zero-shot-video-question-answer-on-egoschema-1 | VideoChat-T (7B) | #11 | Accuracy: 60.0 |
| zero-shot-video-question-answer-on-video-mme | VideoChat-T (7B) | #6 | Accuracy (%): 46.3 |
| zero-shot-video-question-answer-on-video-mme-1 | VideoChat-T (7B) | #9 | Accuracy (%): 55.8 |