| action-classification-on-kinetics-400 | VATT-Large | #71 | Acc@1: 82.1Acc@5: 95.5 |
| action-classification-on-kinetics-600 | VATT-Large | #31 | Top-1 Accuracy: 83.6Top-5 Accuracy: 96.6 |
| action-classification-on-moments-in-time | VATT-Large | #5 | Top 1 Accuracy: 41.1Top 5 Accuracy: 67.7 |
| audio-classification-on-audioset | VATT-Base | #37 | Test mAP: 0.394AUC: 0.971d-prime: 2.895 |
| zero-shot-video-retrieval-on-msr-vtt | VATT-MBS | #35 | text-to-video R@10: 29.7text-to-video Median Rank: 49 |
| zero-shot-video-retrieval-on-youcook2 | VATT-MBS | #6 | text-to-video R@10: 45.5text-to-video Mean Rank: 13 |