Metric: Top-1 Noun (higher is better)
| # | Model↕ | Top-1 Noun▼ | Augmentations | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Audiovisual Masked Autoencoder (Audiovisual, Single) | 56.4 | Yes | Audiovisual Masked Autoencoders | 2022-12-09 | Code |
| 2 | Audiovisual Masked Autoencoder (Video-only, Single) | 55.9 | Yes | Audiovisual Masked Autoencoders | 2022-12-09 | Code |
| 3 | Audiovisual Masked Autoencoder (Audio-only, Single) | 27.2 | Yes | Audiovisual Masked Autoencoders | 2022-12-09 | Code |
| 4 | PlayItBackX3 | 23.1 | No | Play It Back: Iterative Attention for Audio Reco... | 2022-10-20 | Code |