Measuring Visual Surprise Jointly from Intrinsic and Extrinsic Contexts   for Image Saliency Estimation

doi:10.1007/s11263-016-0892-7

CORC > 北京大学 > 信息科学技术学院

	Measuring Visual Surprise Jointly from Intrinsic and Extrinsic Contexts for Image Saliency Estimation
	Li, Jia ; Tian, Yonghong ; Chen, Xiaowu ; Huang, Tiejun
刊名	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2016
关键词	Image saliency Visual surprise Intrinsic context Extrinsic context Gaussian mixture model Markov chain ATTENTION FEATURES PREDICT SEARCH SCENES MODEL
DOI	10.1007/s11263-016-0892-7
英文摘要	Detecting conspicuous image content is a challenging task in the field of computer vision. In existing studies, most approaches focus on estimating saliency only with the cues from the input image. However, such "intrinsic" cues are often insufficient to distinguish targets and distractors that may share some common visual attributes. To address this problem, we present an approach to estimate image saliency by measuring the joint visual surprise from intrinsic and extrinsic contexts. In this approach, a hierarchical context model is first built on a database of 31.2 million images, where a Gaussian mixture model (GMM) is trained for each leaf node to encode the prior knowledge on "what is where" in a specific scene. For a testing image that shares similar spatial layout within a scene, the pre-trained GMM can serve as an extrinsic context model to measure the "surprise" of an image patch. Since human attention may quickly shift between different surprising locations, we adopt a Markov chain to model a surprise-driven attention-shifting process so as to infer the salient patches that can best capture human attention. Experiments show that our approach outperforms 19 state-of-the-art methods in fixation prediction.; National Basic Research Program of China [2015CB351806]; National Natural Science Foundation of China [61370113, 61532003, 61390515, 61421062]; Fundamental Research Funds for the Central Universities; SCI(E); EI; ARTICLE; jiali@buaa.edu.cn; yhtian@pku.edu.cn; 1; 44-60; 120
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/447917]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Li, Jia,Tian, Yonghong,Chen, Xiaowu,et al. Measuring Visual Surprise Jointly from Intrinsic and Extrinsic Contexts for Image Saliency Estimation[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2016.
APA	Li, Jia,Tian, Yonghong,Chen, Xiaowu,&Huang, Tiejun.(2016).Measuring Visual Surprise Jointly from Intrinsic and Extrinsic Contexts for Image Saliency Estimation.INTERNATIONAL JOURNAL OF COMPUTER VISION.
MLA	Li, Jia,et al."Measuring Visual Surprise Jointly from Intrinsic and Extrinsic Contexts for Image Saliency Estimation".INTERNATIONAL JOURNAL OF COMPUTER VISION (2016).