Stacked Attention Networks for Image Question Answering

被引：1169

作者：

Yang, Zichao ^{[1
]}

He, Xiaodong ^{[2
]}

Gao, Jianfeng ^{[2
]}

Deng, Li ^{[2
]}

Smola, Alex ^{[1
]}

机构：

[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA

[2] Microsoft Res, Redmond, WA 98052 USA

来源：

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2016年

关键词：

D O I：

10.1109/CVPR.2016.10

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：21 / 29

页数：9