Multiview Spectral Embedding

doi:10.1109/TSMCB.2009.2039566

	Multiview Spectral Embedding
	Xia, Tian 1; Tao, Dacheng 2; Mei, Tao 3; Zhang, Yongdong 1
	2010-12-01
发表期刊	IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS
ISSN	1083-4419
卷号	40 期号:6 页码:1438-1446
摘要	In computer vision and multimedia search, it is common to use multiple features from different views to represent an object. For example, to well characterize a natural scene image, it is essential to find a set of visual features to represent its color, texture, and shape information and encode each feature into a vector. Therefore, we have a set of vectors in different spaces to represent the image. Conventional spectral-embedding algorithms cannot deal with such datum directly, so we have to concatenate these vectors together as a new vector. This concatenation is not physically meaningful because each feature has a specific statistical property. Therefore, we develop a new spectral-embedding algorithm, namely, multiview spectral embedding (MSE), which can encode different features in different ways, to achieve a physically meaningful embedding. In particular, MSE finds a low-dimensional embedding wherein the distribution of each view is sufficiently smooth, and MSE explores the complementary property of different views. Because there is no closed-form solution for MSE, we derive an alternating optimization-based iterative algorithm to obtain the low-dimensional embedding. Empirical evaluations based on the applications of image retrieval, video annotation, and document clustering demonstrate the effectiveness of the proposed approach.
关键词	Dimensionality reduction multiple views spectral embedding
DOI	10.1109/TSMCB.2009.2039566
收录类别	SCI
语种	英语
资助项目	National Basic Research Program of China (973 Program)[2007CB311100] ; National High-Technology Research and Development Program of China (863 Program)[2007AA01Z416] ; National Natural Science Foundation of China[60873165] ; National Natural Science Foundation of China[60802028] ; National Natural Science Foundation of China[60902090] ; Beijing New Star Project on Science and Technology[2007B071] ; Beijing Municipal Education Commission ; Nanyang Technological University Nanyang SUG[M58020010] ; Microsoft Operations PTE LTD-NTU Joint RD[M48020065] ; K. C. Wong Education Foundation
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000284364400002
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：412[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/2XEOYT63/12190
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xia, Tian
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Ctr Adv Comp Technol Res, Beijing 100190, Peoples R China 2.Nanyang Technol Univ, Sch Comp Engn, Singapore 639798, Singapore 3.Microsoft Res Asia, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Xia, Tian,Tao, Dacheng,Mei, Tao,et al. Multiview Spectral Embedding[J]. IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS,2010,40(6):1438-1446.
APA	Xia, Tian,Tao, Dacheng,Mei, Tao,&Zhang, Yongdong.(2010).Multiview Spectral Embedding.IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS,40(6),1438-1446.
MLA	Xia, Tian,et al."Multiview Spectral Embedding".IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 40.6(2010):1438-1446.