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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 复杂系统认知与决策实验室
  5. 类脑芯片与系统研究
Object Categorization Using Class-Specific Representations

文献类型：期刊论文

作者Zhang, Chunjie1,2; Cheng, Jian2,3,4; Li, Liang5; Li, Changsheng6; Tian, Qi7
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
出版日期2018-09-01
卷号29期号:9页码:4528-4534
关键词Class-specific Representation Image Classification Object Categorization Visual Representation
DOI10.1109/TNNLS.2017.2757497
文献子类Article
英文摘要Object categorization refers to the task of automatically classifying objects based on the visual content. Existing approaches simply represent each image with the visual features without considering the specific characters of images within the same class. However, objects of the same class may exhibit unique characters, which should be represented accordingly. In this brief, we propose a novel class-specific representation strategy for object categorization. For each class, we first model the characters of images within the same class using Gaussian mixture model (GMM). We then represent each image by calculating the Euclidean distance and relative Euclidean distance between the image and the GMM model for each class. We concatenate the representations of each class for joint representation. In this way, we can represent an image by not only considering the visual contents but also combining the class-specific characters. Experiments on several public available data sets validate the superiority of the proposed class-specific representation method over well-established algorithms for object category predictions.
WOS关键词IMAGE CLASSIFICATION ; LOW-RANK ; DICTIONARY ; CODEBOOKS ; KERNEL ; SPACE
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000443083700052
资助机构National Natural Science Foundation of China(61303154 ; Scientific Research Key Program of Beijing Municipal Commission of Education(KZ201610005012) ; ARO(W911NF-15-1-0290) ; NEC Laboratory of America ; National Science Foundation of China(61429201) ; NEC Laboratory of Blippar ; 61332016)
源URL[http://ir.ia.ac.cn/handle/173211/15479]  
专题类脑芯片与系统研究
作者单位1.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100049, Peoples R China
5.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100049, Peoples R China
6.Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 611731, Sichuan, Peoples R China
7.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
推荐引用方式
GB/T 7714		 Zhang, Chunjie,Cheng, Jian,Li, Liang,et al. Object Categorization Using Class-Specific Representations[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(9):4528-4534.
APA Zhang, Chunjie,Cheng, Jian,Li, Liang,Li, Changsheng,&Tian, Qi.(2018).Object Categorization Using Class-Specific Representations.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(9),4528-4534.
MLA Zhang, Chunjie,et al."Object Categorization Using Class-Specific Representations".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.9(2018):4528-4534.

入库方式： OAI收割

来源：自动化研究所

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。