OPT OpenIR  > 光学影像学习与分析中心
Detection of Co-salient Objects by Looking Deep and Wide
Zhang, Dingwen1; Han, Junwei1; Li, Chao1; Wang, Jingdong2; Li, Xuelong3; Han, JW
Department光学影像学习与分析中心
2016-11-01
Source PublicationINTERNATIONAL JOURNAL OF COMPUTER VISION
ISSN0920-5691
Volume120Issue:2Pages:215-232
Contribution Rank3
Abstract

In this paper, we propose a unified co-salient object detection framework by introducing two novel insights: (1) looking deep to transfer higher-level representations by using the convolutional neural network with additional adaptive layers could better reflect the sematic properties of the co-salient objects; (2) looking wide to take advantage of the visually similar neighbors from other image groups could effectively suppress the influence of the common background regions. The wide and deep information are explored for the object proposal windows extracted in each image. The window-level co-saliency scores are calculated by integrating the intra-image contrast, the intra-group consistency, and the inter-group separability via a principled Bayesian formulation and are then converted to the superpixel-level co-saliency maps through a foreground region agreement strategy. Comprehensive experiments on two existing and one newly established datasets have demonstrated the consistent performance gain of the proposed approach.

SubtypeArticle
KeywordCo-saliency Detection Domain Adaptive Convolutional Neural Network Bayesian Framework
Subject AreaComputer Science, Artificial Intelligence
WOS HeadingsScience & Technology ; Technology
DOI10.1007/s11263-016-0907-4
Indexed BySCI
WOS KeywordVISUAL SALIENCY ; SEGMENTATION ; EXTRACTION ; MODEL ; DISCOVERY ; VIDEOS
Language英语
WOS Research AreaComputer Science
Funding OrganizationNational Science Foundation of China(61522207 ; Doctorate Foundation ; Excellent Doctorate Foundation of Northwestern Polytechnical University ; 61473231)
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000382092900006
Citation statistics
Document Type期刊论文
Identifierhttp://ir.opt.ac.cn/handle/181661/28413
Collection光学影像学习与分析中心
Corresponding AuthorHan, JW
Affiliation1.Northwestern Polytech Univ, Sch Automat, Xian 710072, Peoples R China
2.Microsoft Res Asia, Beijing, Peoples R China
3.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Dingwen,Han, Junwei,Li, Chao,et al. Detection of Co-salient Objects by Looking Deep and Wide[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2016,120(2):215-232.
APA Zhang, Dingwen,Han, Junwei,Li, Chao,Wang, Jingdong,Li, Xuelong,&Han, JW.(2016).Detection of Co-salient Objects by Looking Deep and Wide.INTERNATIONAL JOURNAL OF COMPUTER VISION,120(2),215-232.
MLA Zhang, Dingwen,et al."Detection of Co-salient Objects by Looking Deep and Wide".INTERNATIONAL JOURNAL OF COMPUTER VISION 120.2(2016):215-232.
Files in This Item:
File Name/Size DocType Version Access License
Detection of Co-sali(7504KB)期刊论文作者接受稿限制开放CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Dingwen]'s Articles
[Han, Junwei]'s Articles
[Li, Chao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Dingwen]'s Articles
[Han, Junwei]'s Articles
[Li, Chao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Dingwen]'s Articles
[Han, Junwei]'s Articles
[Li, Chao]'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.