| multi-modal-classification-on-vgg-sound | CAV-MAE (Audio-Visual) | #1 | Top-1 Accuracy: 65.9 |
| audio-tagging-on-audioset | CAV-MAE (Audio-Visual) | #2 | mean average precision: 0.512 |
| audio-tagging-on-audioset | CAV-MAE (Audio-Only) | #13 | mean average precision: 0.466 |
| sound-prompted-semantic-segmentation-on-ade20k | CAVMAE | #2 | mAP: 26.0mIoU: 17.0 |
| speech-prompted-semantic-segmentation-on-ade20k | CAVMAE | #2 | mAP: 27.2mIoU: 19.9 |
| audio-classification-on-audioset | CAV-MAE (Audio-Visual) | #3 | Test mAP: 0.512 |
| audio-classification-on-audioset | CAV-MAE (Audio-Only) | #30 | Test mAP: 0.466 |
| audio-classification-on-audioset | CAV-MAE (Visual-Only) | #42 | Test mAP: 0.262 |
| audio-classification-on-vggsound | CAV-MAE (Audio-Visual) | #4 | Top 1 Accuracy: 65.9 |
| audio-classification-on-vggsound | CAV-MAE (Audio-Only) | #8 | Top 1 Accuracy: 59.5 |