UM  > 科技學院  > 電腦及資訊科學系
Multiview dimension reduction via Hessian multiset canonical correlations
Liu, Weifeng1; Yang, Xinghao1; Tao, Dapeng2; Cheng, Jun3,4; Tang, Yuanyan5,6
2018-05
Source PublicationInformation fusion
ISSN1566-2535
Volume41Pages:119-128
Abstract

Canonical correlation analysis (CCA) is a main technique of linear subspace approach for two-view dimension reduction by finding basis vectors with maximum correlation between the pair of variables. The shortcoming of the traditional CCA lies that it only handles data represented by two-view features and cannot reveal the nonlinear correlation relationship. In recent years, many variant algorithms have been developed to extend the capability of CCA such as discriminative CCA, sparse CCA, kernel CCA, locality preserving CCA and multiset canonical correlation analysis (MCCA). One representative work is Laplacian multiset canonical correlations (LapMCC) that employs graph Laplacian to exploit the nonlinear correlation information for multiview high-dimensional data. However, it possibly leads to poor extrapolating power because Laplacian regularization biases the solution towards a constant function. In this paper, we present Hessian multiset canonical correlations (HesMCC) for multiview dimension reduction. Hessian can properly exploit the intrinsic local geometry of the data manifold in contrast to Laplacian. HesMCC takes the advantage of Hessian and provides superior extrapolating capability and finally leverage the performance. Extensive experiments on several popular datasets for handwritten digits classification, face classification and object classification validate the effectiveness of the proposed HesMCC algorithm by comparing it with baseline algorithms including TCCA, KMUDA, MCCA and LapMCC. 

KeywordMultiview Dimension Reduction Hessian Canonical Correlation Analysis
DOIhttps://doi.org/10.1016/j.inffus.2017.09.001
URLView the original
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS IDWOS:000417662100012
PublisherELSEVIER SCIENCE BV, PO BOX 211, 1000 AE AMSTERDAM, NETHERLANDS
The Source to ArticleWOS
Fulltext Access
Citation statistics
Cited Times [WOS]:32   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorLiu, Weifeng; Tao, Dapeng
Affiliation1.College of Information and Control Engineering, China University of Petroleum (East China), Qingdao 266580, Shandong, China
2.School of Information Science and Engineering, Yunnan University, Kunming 650091, Yunnan, China
3.Shenzhen Key Lab for CVPR, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, Guangdong, China
4.The Chinese University of Hong Kong, Hong Kong, China
5.Faculty of Science and Technology, University of Macau, Macau 999078, China
6.College of Computer Science, Chongqing University, Chongqing 400000, China
Recommended Citation
GB/T 7714
Liu, Weifeng,Yang, Xinghao,Tao, Dapeng,et al. Multiview dimension reduction via Hessian multiset canonical correlations[J]. Information fusion,2018,41:119-128.
APA Liu, Weifeng,Yang, Xinghao,Tao, Dapeng,Cheng, Jun,&Tang, Yuanyan.(2018).Multiview dimension reduction via Hessian multiset canonical correlations.Information fusion,41,119-128.
MLA Liu, Weifeng,et al."Multiview dimension reduction via Hessian multiset canonical correlations".Information fusion 41(2018):119-128.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Liu, Weifeng]'s Articles
[Yang, Xinghao]'s Articles
[Tao, Dapeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Liu, Weifeng]'s Articles
[Yang, Xinghao]'s Articles
[Tao, Dapeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Liu, Weifeng]'s Articles
[Yang, Xinghao]'s Articles
[Tao, Dapeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.