ISCAS OpenIR
Accurate and efficient cross-domain visual matching leveraging multiple feature representations
Sun, Gang (1); Wang, Shuhui (3); Liu, Xuehui (1); Huang, Qingming (2); Chen, Yanyun (1); Wu, Enhua (1); Sun, G.(sung@ios.ac.cn)
2013
Pages565-575
Indexed TypeSCI ; EI
Publish PlaceSpringer Verlag
ISSN1782789
Department(1) State Key Laboratory of Computer Science, Institute of Software, Chinese Academy of Sciences, Beijing, China; (2) University of Chinese Academy of Sciences, Beijing, China; (3) Key Laboratory of Intelligent Information Processing (CAS), Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China; (4) University of Macau, China
English AbstractCross-domain visual matching aims at finding visually similar images across a wide range of visual domains, and has shown a practical impact on a number of applications. Unfortunately, the state-of-the-art approach, which estimates the relative importance of the single feature dimensions still suffers from low matching accuracy and high time cost. To this end, this paper proposes a novel cross-domain visual matching framework leveraging multiple feature representations. To integrate the discriminative power of multiple features, we develop a data-driven, query specific feature fusion model, which estimates the relative importance of the individual feature dimensions as well as the weight vector among multiple features simultaneously. Moreover, to alleviate the computational burden of an exhaustive subimage search, we design a speedup scheme, which employs hyperplane hashing for rapidly collecting the hard-negatives. Extensive experiments carried out on various matching tasks demonstrate that the proposed approach outperforms the state-of-the-art in both accuracy and efficiency. © 2013 Springer-Verlag Berlin Heidelberg.; Cross-domain visual matching aims at finding visually similar images across a wide range of visual domains, and has shown a practical impact on a number of applications. Unfortunately, the state-of-the-art approach, which estimates the relative importance of the single feature dimensions still suffers from low matching accuracy and high time cost. To this end, this paper proposes a novel cross-domain visual matching framework leveraging multiple feature representations. To integrate the discriminative power of multiple features, we develop a data-driven, query specific feature fusion model, which estimates the relative importance of the individual feature dimensions as well as the weight vector among multiple features simultaneously. Moreover, to alleviate the computational burden of an exhaustive subimage search, we design a speedup scheme, which employs hyperplane hashing for rapidly collecting the hard-negatives. Extensive experiments carried out on various matching tasks demonstrate that the proposed approach outperforms the state-of-the-art in both accuracy and efficiency. © 2013 Springer-Verlag Berlin Heidelberg.
KeywordVisual Matching Cross-domain Multiple Features Hyperplane Hashing
Language英语
WOS IDWOS:000319478400011
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Content Type会议论文
URIhttp://ir.iscas.ac.cn/handle/311060/16556
Collection中国科学院软件研究所
Corresponding AuthorSun, G.(sung@ios.ac.cn)
Recommended Citation
GB/T 7714
Sun, Gang ,Wang, Shuhui ,Liu, Xuehui ,et al. Accurate and efficient cross-domain visual matching leveraging multiple feature representations[C]. Springer Verlag,2013:565-575.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Sun, Gang (1)]'s Articles
[Wang, Shuhui (3)]'s Articles
[Liu, Xuehui (1)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Sun, Gang (1)]'s Articles
[Wang, Shuhui (3)]'s Articles
[Liu, Xuehui (1)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Sun, Gang (1)]'s Articles
[Wang, Shuhui (3)]'s Articles
[Liu, Xuehui (1)]'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.