UM  > 科技學院  > 電腦及資訊科學系
Image co-saliency detection by propagating superpixel affinities
Tan Z.1; Wan L.2; Feng W.1; Pun C.-M.2
2013-10-18
Conference Name2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP)
Source PublicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Pages2114-2118
Conference DateMAY 26-31, 2013
Conference PlaceVancouver, CANADA
Abstract

Image co-saliency detection is a valuable technique to highlight perceptually salient regions in image pairs. In this paper, we propose a self-contained co-saliency detection algorithm based on superpixel affinity matrix. We first compute both intra and inter similarities of superpixels of image pairs. Bipartite graph matching is applied to determine most reliable inter similarities. To update the similarity score between every two superpixels, we next employ a GPU-based all-pair SimRank algorithm to do propagation on the affinity matrix. Based on the inter superpixel affinities we derive a co-saliency measure that evaluates the foreground cohesiveness and locality compactness of superpixels within one image. The effectiveness of our method is demonstrated in experimental evaluation. © 2013 IEEE.

KeywordAll-pair Sim-rank Bipartite Graph Matching Co-saliency Measure Image Co-saliency Detection Superpixel Affinity Propagation
DOI10.1109/ICASSP.2013.6638027
URLView the original
WOS Research AreaAcoustics ; Engineering
WOS SubjectAcoustics ; Engineering, Electrical & Electronic
WOS IDWOS:000329611502057
Fulltext Access
Citation statistics
Cited Times [WOS]:19   [WOS Record]     [Related Records in WOS]
Document TypeConference paper
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.Tianjin University
2.Universidade de Macau
Recommended Citation
GB/T 7714
Tan Z.,Wan L.,Feng W.,et al. Image co-saliency detection by propagating superpixel affinities[C],2013:2114-2118.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Tan Z.]'s Articles
[Wan L.]'s Articles
[Feng W.]'s Articles
Baidu academic
Similar articles in Baidu academic
[Tan Z.]'s Articles
[Wan L.]'s Articles
[Feng W.]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Tan Z.]'s Articles
[Wan L.]'s Articles
[Feng W.]'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.