Multi-Task Rank Learning for Visual Saliency Estimation

doi:10.1109/TCSVT.2011.2129430

	Multi-Task Rank Learning for Visual Saliency Estimation
	Li, Jia 1,2; Tian, Yonghong 3; Huang, Tiejun 3; Gao, Wen 3
	2011-05-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	21 期号:5 页码:623-636
摘要	Visual saliency plays an important role in various video applications such as video retargeting and intelligent video advertising. However, existing visual saliency estimation approaches often construct a unified model for all scenes, thus leading to poor performance for the scenes with diversified contents. To solve this problem, we propose a multi-task rank learning approach which can be used to infer multiple saliency models that apply to different scene clusters. In our approach, the problem of visual saliency estimation is formulated in a pair-wise rank learning framework, in which the visual features can be effectively integrated to distinguish salient targets from distractors. A multi-task learning algorithm is then presented to infer multiple visual saliency models simultaneously. By an appropriate sharing of information across models, the generalization ability of each model can be greatly improved. Extensive experiments on a public eye-fixation dataset show that our multi-task rank learning approach outperforms 12 state-of-the-art methods remarkably in visual saliency estimation.
关键词	Generalization ability multi-task learning pair-wise rank learning visual saliency
DOI	10.1109/TCSVT.2011.2129430
收录类别	SCI
语种	英语
资助项目	Chinese National Natural Science Foundation[61035001] ; Chinese National Natural Science Foundation[60973055] ; Chinese National Natural Science Foundation[90820003] ; National Basic Research Program of China[2009CB320906] ; Fok Ying Dong Education Foundation[122008]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000290174900009
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：25[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/12787
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Li, Jia
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Grad Univ CAS, Beijing 100049, Peoples R China 3.Peking Univ, Sch Elect Engn & Comp Sci, Natl Engn Lab Video Technol, Key Lab Machine Percept MoE, Beijing 100871, Peoples R China
推荐引用方式 GB/T 7714	Li, Jia,Tian, Yonghong,Huang, Tiejun,et al. Multi-Task Rank Learning for Visual Saliency Estimation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2011,21(5):623-636.
APA	Li, Jia,Tian, Yonghong,Huang, Tiejun,&Gao, Wen.(2011).Multi-Task Rank Learning for Visual Saliency Estimation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,21(5),623-636.
MLA	Li, Jia,et al."Multi-Task Rank Learning for Visual Saliency Estimation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 21.5(2011):623-636.