Generating Question Relevant Captions to Aid Visual Question Answering

Jialin Wu
Jialin Wu
Zeyuan Hu
Zeyuan Hu

ACL (1), pp. 3585-3594, 2019.

被引用0|引用|浏览36|DOI:https://doi.org/10.18653/v1/p19-1348
EI
其它链接dblp.uni-trier.de|arxiv.org

摘要

Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We present a novel approach to improve VQA performance that exploits this connection by jointly generating captions that are targeted to help answer a specific visual question. The model is trained using an exi...更多

代码

数据

下载 PDF 全文
您的评分 :
0

 

标签
评论