中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Probabilistic Multi-Task Learning for Visual Saliency Estimation in Video

文献类型：期刊论文

作者Li, Jia1,3; Tian, Yonghong2; Huang, Tiejun2; Gao, Wen2
刊名INTERNATIONAL JOURNAL OF COMPUTER VISION
出版日期2010-11-01
卷号90期号:2页码:150-165
关键词Visual saliency Probabilistic framework Visual search tasks Multi-task learning
ISSN号0920-5691
DOI10.1007/s11263-010-0354-6
英文摘要In this paper, we present a probabilistic multi-task learning approach for visual saliency estimation in video. In our approach, the problem of visual saliency estimation is modeled by simultaneously considering the stimulus-driven and task-related factors in a probabilistic framework. In this framework, a stimulus-driven component simulates the low-level processes in human vision system using multi-scale wavelet decomposition and unbiased feature competition; while a task-related component simulates the high-level processes to bias the competition of the input features. Different from existing approaches, we propose a multi-task learning algorithm to learn the task-related "stimulus-saliency" mapping functions for each scene. The algorithm also learns various fusion strategies, which are used to integrate the stimulus-driven and task-related components to obtain the visual saliency. Extensive experiments were carried out on two public eye-fixation datasets and one regional saliency dataset. Experimental results show that our approach outperforms eight state-of-the-art approaches remarkably.
资助项目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Computer Science
语种英语
WOS记录号WOS:000281087900002
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/12506]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Tian, Yonghong
作者单位1.Chinese Acad Sci, Grad Univ, Beijing 100049, Peoples R China
2.Peking Univ, Natl Engn Lab Video Technol, Beijing 100871, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Li, Jia,Tian, Yonghong,Huang, Tiejun,et al. Probabilistic Multi-Task Learning for Visual Saliency Estimation in Video[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2010,90(2):150-165.
APA Li, Jia,Tian, Yonghong,Huang, Tiejun,&Gao, Wen.(2010).Probabilistic Multi-Task Learning for Visual Saliency Estimation in Video.INTERNATIONAL JOURNAL OF COMPUTER VISION,90(2),150-165.
MLA Li, Jia,et al."Probabilistic Multi-Task Learning for Visual Saliency Estimation in Video".INTERNATIONAL JOURNAL OF COMPUTER VISION 90.2(2010):150-165.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

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。