Audio Classification On Dcase
評価指標
PRE-TRAINING DATASET
Top-1 Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | PRE-TRAINING DATASET | Top-1 Accuracy | Paper Title | Repository |
|---|---|---|---|---|
| CrissCross (Kinetics-400) | Kinetics-400 | 96 | Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity | |
| CrissCross (AudioSet) | AudioSet | 97 | Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity | |
| XDC | IG-Random | 95 | Self-Supervised Learning by Cross-Modal Audio-Video Clustering | |
| XDC | AudioSet | 95 | Self-Supervised Learning by Cross-Modal Audio-Video Clustering | |
| CrissCross (Kinetics-Sound) | Kinetics-Sound | 93 | Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity |
0 of 5 row(s) selected.