Visual Question Answering On Coco Visual 1
Metrics
Percentage correct
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Percentage correct |
|---|---|
| multimodal-compact-bilinear-pooling-for | 70.1 |
| high-order-attention-models-for-visual | 69.3 |
| co-attending-free-form-regions-and-detections | 70.04 |
| hierarchical-question-image-co-attention-for | 66.1 |
| multimodal-residual-learning-for-visual-qa | 66.3 |
| simple-baseline-for-visual-question-answering | 62.0 |
| r-vqa-learning-visual-relation-facts-with | 69.60 |
| training-recurrent-answering-units-with-joint | 67.3 |
| vqa-visual-question-answering | 63.1 |
| a-focused-dynamic-attention-model-for-visual | 64.2 |