Question-Guided Hybrid Convolution for Visual Question Answering

Open paper
Benchmark Model Rank Results
visual-question-answering-on-clevrQGHC+Att+Concat–Accuracy: 65.90
visual-question-answering-on-coco-vqa-real-images-1-0-open-endedQGHC+Att+Concat–Percentage correct: 65.90

Rank counts only results with a code link.