Finding the Secret of Image Saliency in the Frequency Domain

doi:10.1109/TPAMI.2015.2424870

CORC > 北京大学 > 信息科学技术学院

	Finding the Secret of Image Saliency in the Frequency Domain
	Li, Jia ; Duan, Ling-Yu ; Chen, Xiaowu ; Huang, Tiejun ; Tian, Yonghong
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2015
关键词	Image saliency Fourier transform spectral analysis fixation prediction learning-based experimental study REGION DETECTION VISUAL SALIENCY OBJECT DETECTION DETECTION MODEL VIDEO ATTENTION FEATURES CONTRAST
DOI	10.1109/TPAMI.2015.2424870
英文摘要	There are two sides to every story of visual saliency modeling in the frequency domain. On the one hand, image saliency can be effectively estimated by applying simple operations to the frequency spectrum. On the other hand, it is still unclear which part of the frequency spectrum contributes the most to popping-out targets and suppressing distractors. Toward this end, this paper tentatively explores the secret of image saliency in the frequency domain. From the results obtained in several qualitative and quantitative experiments, we find that the secret of visual saliency may mainly hide in the phases of intermediate frequencies. To explain this finding, we reinterpret the concept of discrete Fourier transform from the perspective of template-based contrast computation and thus develop several principles for designing the saliency detector in the frequency domain. Following these principles, we propose a novel approach to design the saliency detector under the assistance of prior knowledge obtained through both unsupervised and supervised learning processes. Experimental results on a public image benchmark show that the learned saliency detector outperforms 18 state-of-the-art approaches in predicting human fixations.; National Natural Science Foundation of China [61370113, 61325011, 61390515, 61421003]; National Hightech R&D Program of China [2015AA016302]; Supervisor Award Funding for Excellent Doctoral Dissertation of Beijing [20128000103]; Fundamental Research Funds for the Central Universities; SCI(E); EI; ARTICLE; jiali@buaa.edu.cn; lingyu@pku.edu.cn; chen@buaa.edu.cn; tjhuang@pku.edu.cn; yhtian@pku.edu.cn; 12; 2428-2440; 37
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/435628]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Li, Jia,Duan, Ling-Yu,Chen, Xiaowu,et al. Finding the Secret of Image Saliency in the Frequency Domain[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2015.
APA	Li, Jia,Duan, Ling-Yu,Chen, Xiaowu,Huang, Tiejun,&Tian, Yonghong.(2015).Finding the Secret of Image Saliency in the Frequency Domain.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE.
MLA	Li, Jia,et al."Finding the Secret of Image Saliency in the Frequency Domain".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2015).