Learning Conditioned Graph Structures for Interpretable Visual Question Answering

1 code implementation • NeurIPS 2018 • Will Norcliffe-Brown, Efstathios Vafeias, Sarah Parisot

Our method combines a graph learner module, which learns a question specific graph representation of the input image, with the recent concept of graph convolutions, aiming to learn image representations that capture question specific interactions.

Question Answering Visual Question Answering