Stacked Attention Networks for Image Question Answering

Citations Over TimeTop 1% of 2016 papers

Abstract

This paper presents stacked attention networks (SANs) that learn to answer natural language questions from images. SANs use semantic representation of a question as query 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 demonstrate that the proposed SANs significantly outperform previous state-of-the-art approaches. The visualization of the attention layers illustrates the progress that the SAN locates the relevant visual clues that lead to the answer of the question layer-by-layer.

Related Papers

• → Improving the Question Answering Quality using Answer Candidate Filtering based on Natural-Language Features(2021)4 cited
• Question answering systems: a partial answer(2007)
• → Similarity Detection of Natural-Language Questions and Answers using the VANiLLa dataset(2021)2 cited
• → Mobile System Using Natural Language Annotations for Question Answering(2009)1 cited
• → Towards a question answering system based on precisiated natural language(2011)1 cited