Saliency Detection by Multiple-Instance Learning

doi:10.1109/TSMCB.2012.2214210

OPT OpenIR > 光谱成像技术研究室

	Saliency Detection by Multiple-Instance Learning
	Wang, Qi; Yuan, Yuan; Yan, Pingkun; Li, Xuelong
作者部门	光学影像学习与分析中心
	2013-04-01
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
ISSN	2168-2267
卷号	43 期号:2 页码:660-672
产权排序	1
摘要	Saliency detection has been a hot topic in recent years. Its popularity is mainly because of its theoretical meaning for explaining human attention and applicable aims in segmentation, recognition, etc. Nevertheless, traditional algorithms are mostly based on unsupervised techniques, which have limited learning ability. The obtained saliency map is also inconsistent with many properties of human behavior. In order to overcome the challenges of inability and inconsistency, this paper presents a framework based on multiple-instance learning. Low-, mid-, and high-level features are incorporated in the detection procedure, and the learning ability enables it robust to noise. Experiments on a data set containing 1000 images demonstrate the effectiveness of the proposed framework. Its applicability is shown in the context of a seam carving application.
文章类型	Article
关键词	Attention Computer Vision Machine Learning Multiple-instance Learning (Mil) Saliency Saliency Map
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TSMCB.2012.2214210
收录类别	SCI ; EI
关键词[WOS]	SELECTIVE VISUAL-ATTENTION ; REGION DETECTION ; IMAGE SEGMENTATION ; RECOGNITION ; COLOR ; MODEL
语种	英语
WOS研究方向	Computer Science
项目资助者	National Basic Research Program of China (973 Program)(2011CB707104) ; National Natural Science Foundation of China(61172143 ; Natural Science Foundation Research Project of Shaanxi Province(2012JM8024) ; 50th China Postdoctoral Science Foundation(2011M501487) ; 61105012 ; 61072093 ; 611721412 ; 61125106 ; 91120302)
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000317644300021
引用统计	被引频次：158[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.opt.ac.cn/handle/181661/23190
专题	光谱成像技术研究室
作者单位	Chinese Acad Sci, Ctr OPT IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China
推荐引用方式 GB/T 7714	Wang, Qi,Yuan, Yuan,Yan, Pingkun,et al. Saliency Detection by Multiple-Instance Learning[J]. IEEE TRANSACTIONS ON CYBERNETICS,2013,43(2):660-672.
APA	Wang, Qi,Yuan, Yuan,Yan, Pingkun,&Li, Xuelong.(2013).Saliency Detection by Multiple-Instance Learning.IEEE TRANSACTIONS ON CYBERNETICS,43(2),660-672.
MLA	Wang, Qi,et al."Saliency Detection by Multiple-Instance Learning".IEEE TRANSACTIONS ON CYBERNETICS 43.2(2013):660-672.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Saliency Detection b（2341KB）	期刊论文	出版稿	限制开放	CC BY	请求全文