Audio Classification On Epic Kitchens 100
Metrics
Top-1 Action
Top-1 Noun
Top-1 Verb
Results
Performance results of various models on this benchmark
Model Name | Top-1 Action | Top-1 Noun | Top-1 Verb | Paper Title | Repository |
|---|---|---|---|---|---|
| Audiovisual Masked Autoencoder (Video-only, Single) | 45.8 | 55.9 | 70.8 | Audiovisual Masked Autoencoders | |
| Audiovisual Masked Autoencoder (Audiovisual, Single) | 46.0 | 56.4 | 71.4 | Audiovisual Masked Autoencoders | |
| PlayItBackX3 | 15.9 | 23.1 | 47 | Play It Back: Iterative Attention for Audio Recognition | |
| Audiovisual Masked Autoencoder (Audio-only, Single) | 19.7 | 27.2 | 52.7 | Audiovisual Masked Autoencoders |
0 of 4 row(s) selected.