期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 37, 期 12, 页码 2428-2440出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2015.2424870
关键词
Image saliency; Fourier transform; spectral analysis; fixation prediction; learning-based; experimental study
资金
- 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
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据