Visual Question Answering On Visual7W
Metrics
Percentage correct
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Percentage correct |
|---|---|
| coarse-to-fine-reasoning-for-visual-question | 71.9 |
| compact-trilinear-interaction-for-visual | 72.3 |
| modeling-relationships-in-referential | 72.53 |
| multimodal-compact-bilinear-pooling-for | 62.2 |