| audio-classification-on-esc-50 | AVID | #19 | Top-1 Accuracy: 89.2 |
| self-supervised-action-recognition-on-hmdb51 | AVID+CMA (Modified R2+1D-18 on Audioset) | #16 | Top-1 Accuracy: 64.7Pre-Training Dataset: Audioset (Video+Audio)… |
| self-supervised-action-recognition-on-hmdb51 | AVID (Modified R2+1D-18 on Audioset) | #19 | Top-1 Accuracy: 64.1Pre-Training Dataset: Audioset (Video+Audio)… |
| self-supervised-action-recognition-on-hmdb51 | AVID+CMA (Modified R2+1D-18 on Kinetics) | #24 | Top-1 Accuracy: 60.8Pre-Training Dataset: Kinetics400 (Video+Audio)… |
| self-supervised-action-recognition-on-hmdb51 | AVID (Modified R2+1D-18 on Kinetics) | #26 | Top-1 Accuracy: 59.9Pre-Training Dataset: Kinetics400 (Video+Audio)… |
| self-supervised-action-recognition-on-hmdb51-1 | AVID | #7 | Top-1 Accuracy: 64.7 |
| self-supervised-action-recognition-on-ucf101 | AVID+CMA (Modified R2+1D-18 on Audioset) | #17 | 3-fold Accuracy: 91.5Pre-Training Dataset: Audioset (Audio+Video)… |
| self-supervised-action-recognition-on-ucf101 | AVID (Modified R2+1D-18 on Audioset) | #20 | 3-fold Accuracy: 91.0Pre-Training Dataset: Audioset (Audio+Video)… |
| self-supervised-action-recognition-on-ucf101 | AVID+CMA (Modified R2+1D-18 on Kinetics) | #25 | 3-fold Accuracy: 87.5Pre-Training Dataset: Kinetics400 (Audio+Video)… |
| self-supervised-action-recognition-on-ucf101 | AVID (Modified R2+1D-18 on Kinetics) | #26 | 3-fold Accuracy: 86.9Pre-Training Dataset: Kinetics400 (Audio+Video)… |
| self-supervised-action-recognition-on-ucf101-1 | AVID | #6 | 3-fold Accuracy: 91.5 |