CASIA OpenIR  > 类脑智能研究中心
Multi-View Label Sharing For Visual Representations And Classifications
Zhang CJ(张淳杰); Cheng J(程健); Tian Q(田奇)
Source PublicationIEEE Transactions on Multimedia
2017
Issue0Pages:0
AbstractDifferent views represent different aspects of images. It is more effective to combine them for visual classifications. This paper proposes a novel multi-view label sharing method to combine the discriminative power of different views for classifications. Specially, we linearly transfer different views into a shared space for representations. The inter-view similarities are kept in the shared space for each view. We also ensure the intra-view similarities of the same class between different views are preserved in the shared space. We jointly learn the classifiers and transformation matrixes by minimizing the summed classification loss along with the inter-view and intra-view similarity constraints. In this paper, the inter-view constraints refer to the similarities between images of the corresponding view while the inter-view constraints refer to the similarities between different views of images with the same semantics. Experimental results and analysis on several public datasets show the effectiveness of the proposed multi-view label sharing method (MVLS) for visual classifications.
KeywordMulti-view Learning Linear Transformation Shared Space Image Representation Visual Classification
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15320
Collection类脑智能研究中心
Affiliation1.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China.
2.University of Chinese Academy of Sciences, 100049, Beijing, China.
3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, P.O.Box 2728, Beijing, China.
4.Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences, Beijing, China.
5.Department of Computer Science, University of Texas at San Antonio, One UTSA Circle, San Antonio, TX 78249-1604, USA.
Recommended Citation
GB/T 7714
Zhang CJ,Cheng J,Tian Q. Multi-View Label Sharing For Visual Representations And Classifications[J]. IEEE Transactions on Multimedia,2017(0):0.
APA Zhang CJ,Cheng J,&Tian Q.(2017).Multi-View Label Sharing For Visual Representations And Classifications.IEEE Transactions on Multimedia(0),0.
MLA Zhang CJ,et al."Multi-View Label Sharing For Visual Representations And Classifications".IEEE Transactions on Multimedia .0(2017):0.
Files in This Item: Download All
File Name/Size DocType Version Access License
final version (MM-00(2096KB) 开放获取--View Download
tmm 录用邮件.pdf(129KB) 开放获取--View Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang CJ(张淳杰)]'s Articles
[Cheng J(程健)]'s Articles
[Tian Q(田奇)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang CJ(张淳杰)]'s Articles
[Cheng J(程健)]'s Articles
[Tian Q(田奇)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang CJ(张淳杰)]'s Articles
[Cheng J(程健)]'s Articles
[Tian Q(田奇)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: final version (MM-007933).pdf
Format: Adobe PDF
File name: tmm 录用邮件.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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