Textual-Visual Reference-Aware Attention Network for Visual Dialog

doi:10.1109/TIP.2020.2992888

	Textual-Visual Reference-Aware Attention Network for Visual Dialog
	Guo, Dan 1; Wang, Hui 1; Wang, Shuhui 2; Wang, Meng 1
	2020
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
卷号	29 页码:6655-6666
摘要	Visual dialog is a challenging task in multimedia understanding, which requires the dialog agent to answer a series of questions that are based on an input image. The critical issue to produce an exact answer is how to model the mutual semantic interaction among feature representations of the image, question-answer history, and current question. In this study, we propose a textual-visual Reference-Aware Attention Network (RAA-Net), which aims to effectively fuse Q (question), H (history), V-l (local vision), and V-g (global vision) to infer the exact answer. In the multimodal feature flows, RAA-Net first learns the textual context through multi-head attention between Q and H and then guides the textual reference semantics to the image to capture visual reference semantics by self- and cross-reference-aware attention in and between V-l and V-g. In the proposed RAA-Net, we exploit the two-stage (intra- and inter-) visual reasoning mechanism on V-l and V-g. Extensive experiments on the VisDial v0.9 and v1.0 datasets show that RAA-Net achieves state-of-the-art performance. Visualization results on both visual and textual attention maps further validate the remarkable interpretability achieved by our solution.
关键词	Visual dialog attention network textual reference visual reference multimodal semantic interaction
DOI	10.1109/TIP.2020.2992888
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China (NSFC)[61725203] ; National Natural Science Foundation of China (NSFC)[61732008] ; National Natural Science Foundation of China (NSFC)[61672497] ; National Natural Science Foundation of China (NSFC)[61876058]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000545739000006
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：17[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/15074
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Meng
作者单位	1.Hefei Univ Technol, Sch Comp Sci & Informat Engn, Hefei 230601, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Guo, Dan,Wang, Hui,Wang, Shuhui,et al. Textual-Visual Reference-Aware Attention Network for Visual Dialog[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:6655-6666.
APA	Guo, Dan,Wang, Hui,Wang, Shuhui,&Wang, Meng.(2020).Textual-Visual Reference-Aware Attention Network for Visual Dialog.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,6655-6666.
MLA	Guo, Dan,et al."Textual-Visual Reference-Aware Attention Network for Visual Dialog".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):6655-6666.