| Benchmark | Model | Rank | Results |
|---|---|---|---|
| action-recognition-on-epic-kitchens-100 | AVT | – | Action@1: 47.2Verb@1: 70.4Noun@1: 59.3 |
| audio-classification-on-vggsound | AVT (Audio-Visual) | – | Top 1 Accuracy: 63.9Top 5 Accuracy: 85.0 |
| audio-classification-on-vggsound | AVT (V) | – | Top 1 Accuracy: 53.2Top 5 Accuracy: 74.8 |
| multi-modal-classification-on-vgg-sound | AVT | – | Top-1 Accuracy: 63.9Top-5 Accuracy: 85.0 |