Explanation guided cross-modal social image clustering

doi:10.1016/j.ins.2022.01.065

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Explanation guided cross-modal social image clustering
	Yan, Xiaoqiang 1; Mao, Yiqiao 1; Ye, Yangdong 1; Yu, Hui 2; Wang, Fei-Yue3,4,5
发表期刊	INFORMATION SCIENCES
ISSN	0020-0255
	2022-05-01
卷号	593 页码:1-16
通讯作者	Ye, Yangdong(ieydye@zzu.edu.cn)
摘要	The integration of visual and semantic information has been found to play a role in increasing the accuracy of social image clustering methods. However, existing approaches are limited by the heterogeneity gap between the visual and semantic modalities, and their performances significantly degrade due to the commonly sparse and incomplete tags in semantic modality. To address these problems, we propose a novel clustering framework to discover reasonable categories in unlabeled social images under the guidance of human explanations. First of all, a novel Explanation Generation Model (EGM) is proposed to automatically boost textual information for the sparse and incomplete tags based on an extra lexical database with human knowledge. Then, a novel clustering algorithm called Group Constrained Information Maximization (GCIM) is proposed to learn image categories. In this algorithm, a new type of constraint named group level side information is unprecedentedly defined to bridge the well-known heterogeneity gap between visual and textual modalities. Finally, an interactive draw-and-merge optimization method is proposed to ensure an optimal solution. Extensive experiments on several social image datasets including NUS-Wide, IAPRTC, MIRFlickr, ESP-Game and COCO demonstrate the superiority of the proposed approach to state-of-the-art baselines. (c) 2022 Elsevier Inc. All rights reserved.
关键词	Social image clustering Human explanation Side information Information maximization Interactive optimization
DOI	10.1016/j.ins.2022.01.065
关键词[WOS]	INFORMATION BOTTLENECK ; MULTIVIEW
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61906172] ; National Natural Science Foundation of China[62176239] ; Postdoctoral Research Foundation of China[2020M682357] ; EPSRC through project 4D Facial Sensing and Modelling[EP/N025849/1]
项目资助者	National Natural Science Foundation of China ; Postdoctoral Research Foundation of China ; EPSRC through project 4D Facial Sensing and Modelling
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000770686400001
出版者	ELSEVIER SCIENCE INC
引用统计	被引频次：8[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/48229
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Ye, Yangdong
作者单位	1.Zhengzhou Univ, Sch Informat Engn, Zhengzhou 450052, Peoples R China 2.Univ Portsmouth, Sch Creat Technol, Portsmouth PO1 2DJ, Hants, England 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 4.Macau Univ Sci & Technol, Inst Syst Engn, Taipa 999078, Macao, Peoples R China 5.Qingdao Acad Intelligent Ind, Qingdao 266109, Peoples R China
推荐引用方式 GB/T 7714	Yan, Xiaoqiang,Mao, Yiqiao,Ye, Yangdong,et al. Explanation guided cross-modal social image clustering[J]. INFORMATION SCIENCES,2022,593:1-16.
APA	Yan, Xiaoqiang,Mao, Yiqiao,Ye, Yangdong,Yu, Hui,&Wang, Fei-Yue.(2022).Explanation guided cross-modal social image clustering.INFORMATION SCIENCES,593,1-16.
MLA	Yan, Xiaoqiang,et al."Explanation guided cross-modal social image clustering".INFORMATION SCIENCES 593(2022):1-16.