Measuring Visual Saliency by Site Entropy Rate | |
Wang, Wei ; Wang, Yizhou ; Huang, Qingming ; Gao, Wen | |
2010 | |
英文摘要 | In this paper, we propose a new computational model for visual saliency derived from the information maximization principle. The model is inspired by a few well acknowledged biological facts. To compute the saliency spots of an image, the model first extracts a number of sub-band feature maps using learned sparse codes. It adopts a fully-connected graph representation for each feature map, and runs random walks on the graphs to simulate the signal/information transmission among the interconnected neurons. We propose a new visual saliency measure called Site Entropy Rate (SER) to compute the average information transmitted from anode (neuron) to all the others during the random walk on the graphs/network. This saliency definition also explains the center-surround mechanism from computation aspect. We further extend our model to spatial-temporal domain so as to detect salient spots in videos. To evaluate the proposed model, we do extensive experiments on psychological stimuli, two well known image datasets, as well as a public video dataset. The experiments demonstrate encouraging results that the proposed model achieves the state-of-the-art performance of saliency detection in both still images and videos.; Computer Science, Artificial Intelligence; Computer Science, Software Engineering; Mathematics, Applied; Imaging Science & Photographic Technology; EI; CPCI-S(ISTP); 46 |
语种 | 英语 |
DOI标识 | 10.1109/CVPR.2010.5539927 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/406180] ![]() |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Wang, Wei,Wang, Yizhou,Huang, Qingming,et al. Measuring Visual Saliency by Site Entropy Rate. 2010-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论