Classification on VGG-Sound

Metric: Top-1 Accuracy (higher is better)

LeaderboardDataset
Loading chart...
#ModelTop-1 AccuracyAugmentationsPaperDateCode
1MMT66.2No---
2CAV-MAE (Audio-Visual)65.9YesContrastive Audio-Visual Masked Autoencoder2022-10-02Code
3UAVM65.8YesUAVM: Towards Unifying Audio and Visual Models2022-07-29Code
4AVT63.9No---