UM
Cross-domain recognition by identifying compact joint subspaces
Lin, Yuewei1; Chen, Jing2; Cao, Yu3; Zhou, Youjie1; Zhang, Lingfeng4; Wang, Song1
2015-12-09
Conference NameIEEE International Conference on Image Processing, ICIP 2015
Source PublicationProceedings - International Conference on Image Processing, ICIP
Volume2015-December
Pages3461-3465
Conference Date9 27, 2015 - 9 30, 2015
Conference PlaceQuebec City, QC, Canada
Author of SourceIEEE Computer Society
AbstractThis paper introduces a new method to solve the cross-domain recognition problem. Different from the traditional domain adaption methods which rely on a global domain shift for all classes between source and target domain, the proposed method is more flexible to capture individual class variations across domains. We propose to solves the problem by finding the compact joint subspaces of source and target domain. We evaluate the proposed method on two widely used datasets and comparison results demonstrates that the proposed method outperforms the comparison methods. © 2015 IEEE.
DOI10.1109/ICIP.2015.7351447
Language英语
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionUniversity of Macau
Affiliation1.University of South Carolina, United States;
2.University of Macau, China;
3.IBM Research - Almaden, United States;
4.University of Houston, United States
Recommended Citation
GB/T 7714
Lin, Yuewei,Chen, Jing,Cao, Yu,et al. Cross-domain recognition by identifying compact joint subspaces[C]//IEEE Computer Society,2015:3461-3465.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Lin, Yuewei]'s Articles
[Chen, Jing]'s Articles
[Cao, Yu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lin, Yuewei]'s Articles
[Chen, Jing]'s Articles
[Cao, Yu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lin, Yuewei]'s Articles
[Chen, Jing]'s Articles
[Cao, Yu]'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.