Cluster-sensitive Structured Correlation Analysis for Web cross-modal retrieval

doi:10.1016/j.neucom.2015.05.049

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Cluster-sensitive Structured Correlation Analysis for Web cross-modal retrieval
	Wang, Shuhui 1; Zhuang, Fuzhen 1; Jiang, Shuqiang 1; Huang, Qingming 1,2; Tian, Qi 3
刊名	NEUROCOMPUTING
	2015-11-30
卷号	168 页码:747-760
关键词	Correlation learning Cluster-sensitive Structured correlation model Correspondence missing
ISSN号	0925-2312
DOI	10.1016/j.neucom.2015.05.049
英文摘要	Modern cross-modal retrieving technology is required to find semantically relevant content from heterogeneous modalities. As previous studies construct unified dense correlation models on small scale cross-modal data, they are not capable of processing large scale Web data, because (a) the content of Web cross media is divergent; (b) the topic sensitive structure information in the high dimensional space is neglected; and (c) data should be organized as strictly corresponding pairs, which is not satisfied in real world scenarios. To address these challenges, we propose a cluster-sensitive cross-modal correlation learning framework. First, a set of cluster-sensitive correlation sub-models are learned instead of a unified correlation model, which better fits the content divergence in different modalities. We impose structured sparsity regularization on the projection vectors to learn a set of interpretable structured sparse correlation sub-models. Second, to compensate for the correspondence missing, we take full advantage of both intra-modal affinity and inter-modal co-occurrence. The projected coordinates of adjacent data within a modality tend to be similar, and the inconsistency of cluster-sensitive projection is minimized. The learned correlation model adapts to the content divergence and thus achieves better model generality and bias-variance trade-off. Extensive experiments on two large scale cross-modal data demonstrate the effectiveness of our approach. (C) 2015 Elsevier B.V. All rights reserved.
资助项目	National Basic Research Program of China (973 Program)[2012CB316400] ; National Basic Research Program of China (973 Program)[2015CB351802] ; 863 program of China[2014AA015202] ; National Natural Science Foundation of China (NSFC)[61025011] ; National Natural Science Foundation of China (NSFC)[61303160] ; National Natural Science Foundation of China (NSFC)[61332016] ; National Natural Science Foundation of China (NSFC)[61390511] ; National Natural Science Foundation of China (NSFC)[61322212] ; National Natural Science Foundation of China (NSFC)[61473273] ; National Natural Science Foundation of China (NSFC)[61429201] ; ARO Grant[W911NF-12-1-0057] ; NEC Laboratories of America
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER SCIENCE BV
WOS记录号	WOS:000359165000074
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/9519]
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, Shuhui
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intellectual Informat Proc, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
推荐引用方式 GB/T 7714	Wang, Shuhui,Zhuang, Fuzhen,Jiang, Shuqiang,et al. Cluster-sensitive Structured Correlation Analysis for Web cross-modal retrieval[J]. NEUROCOMPUTING,2015,168:747-760.
APA	Wang, Shuhui,Zhuang, Fuzhen,Jiang, Shuqiang,Huang, Qingming,&Tian, Qi.(2015).Cluster-sensitive Structured Correlation Analysis for Web cross-modal retrieval.NEUROCOMPUTING,168,747-760.
MLA	Wang, Shuhui,et al."Cluster-sensitive Structured Correlation Analysis for Web cross-modal retrieval".NEUROCOMPUTING 168(2015):747-760.