Stacked Attention Networks for Image Question Answering 论文

2016引用 2072

Multimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot LearningAdvanced Image and Video Retrieval Techniques

人工智能 Domain Adaptation and Few-Shot Learning Advanced Image and Video Retrieval Techniques Multimodal Machine Learning Applications

关系图谱

作者

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.

作者查看全部 (3)

Alex Smola

Jianfeng Gao

Zichao Yang

Stacked Attention Networks for Image Question Answering 论文

详细信息

摘要

作者查看全部 (3)

相关技术查看全部 (3)

相关事件

相关文章