Visual Question Answering On Vqa V1 Test Dev
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| dual-attention-networks-for-multimodal | 64.3 |
| dynamic-memory-networks-for-visual-and | 60.3 |
| show-ask-attend-and-answer-a-strong-baseline | 64.5 |
| training-recurrent-answering-units-with-joint | 63.3 |
| neural-module-networks | 58.6 |
| hierarchical-question-image-co-attention-for | 61.8 |
| multimodal-compact-bilinear-pooling-for | 64.2 |