CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
Salient Object Detection via Structured Matrix Decomposition
Peng, Houwen1,2; Li, Bing1; Ling, Haibin2; Hu, Weiming1; Xiong, Weihua1; Maybank, Stephen J.3
AbstractLow-rank recovery models have shown potential for salient object detection, where a matrix is decomposed into a low-rank matrix representing image background and a sparse matrix identifying salient objects. Two deficiencies, however, still exist. First, previous work typically assumes the elements in the sparse matrix are mutually independent, ignoring the spatial and pattern relations of image regions. Second, when the low-rank and sparse matrices are relatively coherent, e. g., when there are similarities between the salient objects and background or when the background is complicated, it is difficult for previous models to disentangle them. To address these problems, we propose a novel structured matrix decomposition model with two structural regularizations: (1) a tree-structured sparsity-inducing regularization that captures the image structure and enforces patches from the same object to have similar saliency values, and (2) a Laplacian regularization that enlarges the gaps between salient objects and the background in feature space. Furthermore, high-level priors are integrated to guide the matrix decomposition and boost the detection. We evaluate our model for salient object detection on five challenging datasets including single object, multiple objects and complex scene images, and show competitive results as compared with 24 state-of-the-art methods in terms of seven performance metrics.
KeywordSalient Object Detection Matrix Decomposition Low Rank Structured Sparsity Subspace Learning
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding Organization973 basic research program of China(2014CB349303) ; Natural Science Foundation of China(61472421 ; Strategic Priority Research Program of the CAS(XDB02070003) ; US National Science Foundation Grants(IIS-1218156 ; 61370038 ; IIS-1350521) ; 61303086)
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000397717600016
Citation statistics
Cited Times:64[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Affiliation1.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China
2.Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 USA
3.Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Peng, Houwen,Li, Bing,Ling, Haibin,et al. Salient Object Detection via Structured Matrix Decomposition[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2017,39(4):818-832.
APA Peng, Houwen,Li, Bing,Ling, Haibin,Hu, Weiming,Xiong, Weihua,&Maybank, Stephen J..(2017).Salient Object Detection via Structured Matrix Decomposition.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,39(4),818-832.
MLA Peng, Houwen,et al."Salient Object Detection via Structured Matrix Decomposition".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 39.4(2017):818-832.
Files in This Item: Download All
File Name/Size DocType Version Access License
TPAMI07464858.pdf(3573KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Peng, Houwen]'s Articles
[Li, Bing]'s Articles
[Ling, Haibin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Peng, Houwen]'s Articles
[Li, Bing]'s Articles
[Ling, Haibin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Peng, Houwen]'s Articles
[Li, Bing]'s Articles
[Ling, Haibin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: TPAMI07464858.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.

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