Audio-visual classification on AudioSet
55.85Top-1 AccuracyAVAGENT
Evaluation Results
| Method | Links | |
|---|---|---|
| AVAGENTEvaluation Protocol=Fine-tuning2024.10 | 55.85 | |
| MAVILEvaluation Protocol=Fine-tuning2024.10 | 53.38 | |
| AV-MAEEvaluation Protocol=Fine-tuning2024.10 | 51.32 | |
| CAV-MAEEvaluation Protocol=Fine-tuning2024.10 | 51.29 | |
| AVAGENTEvaluation Protocol=Linear Probing2024.10 | 47.52 | |
| AudioMAEEvaluation Protocol=Fine-tuning2024.10 | 44.92 | |
| MAVILEvaluation Protocol=Linear Probing2024.10 | 43.62 | |
| AV-MAEEvaluation Protocol=Linear Probing2024.10 | 41.67 | |
| CAV-MAEEvaluation Protocol=Linear Probing2024.10 | 40.56 | |
| AudioMAEEvaluation Protocol=Linear Probing2024.10 | 30.23 | |
| MAEEvaluation Protocol=Fine-tuning2024.10 | 24.23 | |
| MAEEvaluation Protocol=Linear Probing2024.10 | 11.52 |