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
Boosted random contextual semantic space based representation for visual recognition

文献类型：期刊论文

作者Zhang, Chunjie1; Xue, Zhe1; Zhu, Xiaobin3; Wang, Huanian4; Huang, Qingming1,5; Tian, Qi2
刊名INFORMATION SCIENCES
出版日期2016-11-10
卷号369页码:160-170
关键词Pattern recognition Image processing Visual representation
ISSN号0020-0255
DOI10.1016/j.ins.2016.06.029
英文摘要Visual information has been widely used for image representation. Although proven very effective, the visual representation lacks explicit semantics. However, how to generate a proper semantic space for image representation is still an open problem that needs to be solved. To jointly model the visual and semantic representations of images, we propose a boosted random contextual semantic space based image representation method. Images are initially represented using local feature's distribution histograms. The semantic space is generated by randomly selecting training images. Images are then mapped into the semantic space accordingly. Semantic context is explored to model the correlations of different semantics which is then used for classification. The classification results are used to re-weight training images in a boosted way. The re-weighted images are used to construct new semantic space for classification. In this way, we are able to jointly consider the visual and semantic information of images. Image classification experiments on several public datasets show the effectiveness of the proposed method. (C) 2016 Elsevier Inc. All rights reserved.
资助项目National Natural Science Foundation of China[61303154] ; National Natural Science Foundation of China[61332016] ; National Basic Research Program of China (973 Program)[2012CB316400] ; National Basic Research Program of China (973 Program)[2015CB351802] ; Open Project of Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000383292500011
出版者ELSEVIER SCIENCE INC
源URL[http://119.78.100.204/handle/2XEOYT63/8146]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhu, Xiaobin
作者单位1.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China
2.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
3.Beijing Technol & Business Univ, Beijing, Peoples R China
4.Cent Univ Finance & Econ, Beijing, Peoples R China
5.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		 Zhang, Chunjie,Xue, Zhe,Zhu, Xiaobin,et al. Boosted random contextual semantic space based representation for visual recognition[J]. INFORMATION SCIENCES,2016,369:160-170.
APA Zhang, Chunjie,Xue, Zhe,Zhu, Xiaobin,Wang, Huanian,Huang, Qingming,&Tian, Qi.(2016).Boosted random contextual semantic space based representation for visual recognition.INFORMATION SCIENCES,369,160-170.
MLA Zhang, Chunjie,et al."Boosted random contextual semantic space based representation for visual recognition".INFORMATION SCIENCES 369(2016):160-170.

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。