| Benchmark | Model | Rank | Results |
|---|---|---|---|
| action-classification-on-kinetics-sounds | CA2ST(B/16) | – | Top 1 Accuracy: 93.3 |
| action-classification-on-kinetics-sounds | CAVA(B/16) | – | Top 1 Accuracy: 92.9 |
| action-recognition-in-videos-on-ucf101 | CA2ST(B/16) | – | 3-fold Accuracy: 97.2 |
| audio-classification-on-vggsound | CA2ST(B/16) | – | Top 1 Accuracy: 68.3 |
| audio-classification-on-vggsound | CAVA(B/16) | – | Top 1 Accuracy: 68.2 |