Bilinear Attention Networks

Benchmark Model Rank Results
phrase-grounding-on-flickr30k-entities-testBAN (Bottom-Up detector)#10R@1: 69.69R@5: 84.22R@10: 86.35
visual-question-answering-on-vqa-v2-test-devBAN+Glove+Counter#28Accuracy: 70.04
visual-question-answering-on-vqa-v2-test-stdBAN+Glove+Counter#24overall: 70.4