Image Captioning by Asking Questions

doi:10.1145/3313873

	Image Captioning by Asking Questions
	Yang, Xiaoshan; XU, Changsheng
刊名	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
	2019-08-01
卷号	15 期号:2 页码:19
关键词	Image captioning visual question answering attention networks
ISSN号	1551-6857
DOI	10.1145/3313873
通讯作者	Yang, Xiaoshan(xiaoshan.yang@nlpr.ia.ac.cn)
英文摘要	Image captioning and visual question answering are typical tasks that connect computer vision and natural language processing. Both of them need to effectively represent the visual content using computer vision methods and smoothly process the text sentence using natural language processing skills. The key problem of these two tasks is to infer the target result based on the interactive understanding of the word sequence and the image. Though they practically use similar algorithms, they are studied independently in the past few years. In this article, we attempt to exploit the mutual correlation between these two tasks. We propose the first VQA-improved image-captioning method that transfers the knowledge learned from the VQA corpora to the image-captioning task. A VQA model is first pretrained on image-question-answer instances. Then, the pretrained VQA model is used to extract VQA-grounded semantic representations according to selected free-form open-ended visual question-answer pairs. The VQA-grounded features are complementary to the visual features, because they interpret images from a different perspective. We incorporate the VQA model into the image-captioning model by adaptively fusing the VQA-grounded feature and the attended visual feature. We show that such simple VQA-improved image-captioning (VQA-IIC) models perform better than conventional image-captioning methods on large-scale public datasets.
资助项目	National Key Research and Development Program of China[2017YFB1002804] ; National Natural Science Foundation of China[61702511] ; National Natural Science Foundation of China[61720106006] ; National Natural Science Foundation of China[61620106003] ; National Natural Science Foundation of China[61432019] ; National Natural Science Foundation of China[61632007] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[U1836220] ; Key Research Program of Frontier Sciences, CAS[QYZDJSSWJSC039] ; Research Program of National Laboratory of Pattern Recognition[Z-2018007] ; CCF-Tencent Open Fund
WOS关键词	VIDEO
WOS研究方向	Computer Science
语种	英语
出版者	ASSOC COMPUTING MACHINERY
WOS记录号	WOS:000482001900008
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; Research Program of National Laboratory of Pattern Recognition ; CCF-Tencent Open Fund
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/27571]
专题	中国科学院自动化研究所
通讯作者	Yang, Xiaoshan
作者单位	Univ Chinese Acad Sci, Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Yang, Xiaoshan,XU, Changsheng. Image Captioning by Asking Questions[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2019,15(2):19.
APA	Yang, Xiaoshan,&XU, Changsheng.(2019).Image Captioning by Asking Questions.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,15(2),19.
MLA	Yang, Xiaoshan,et al."Image Captioning by Asking Questions".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 15.2(2019):19.