Abstract
This paper presents stacked attention networks (SANs)that learn to answer natural language questions from images. SANs use semantic representation of a question asquery to search for the regions in an image that are related to the answer. We argue that image question answering (QA) often requires multiple steps of reasoning. Thus, we develop a multiple-layer SAN in which we query an image multiple times to infer the answer progressively. Experiments conducted on four image QA data sets demonstratethat the proposed SANs significantly outperform previous state-of-the-art approaches. The visualization of the atten-tion layers illustrates the progress that the SAN locates therelevant visual clues that lead to the answer of the questionlayer-by-layer.