Few Shot Action Recognition On Hmdb51
Métriques
1:1 Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | 1:1 Accuracy |
|---|---|
| learn2augment-learning-to-composite-videos | 76.4 |
| few-shot-action-recognition-via-improved | 60.6 |
| spatio-temporal-relation-modeling-for-few | 77.3 |
| temporal-relational-crosstransformers-for-few | 75.6 |
| hybrid-relation-guided-set-matching-for-few | 76.0 |
| depth-guided-adaptive-meta-fusion-network-for | 75.5 |
| Modèle 7 | 62.2 |