Semantically Modeling of Object and Context for Categorization

doi:10.1109/TNNLS.2018.2856096

	Semantically Modeling of Object and Context for Categorization
	Zhang, Chunjie1,2 ; Cheng, Jian2,3,4 ; Tian, Qi 5
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2019-04-01
卷号	30 期号:4 页码:1013-1024
关键词	Context modeling object categorization object modeling semantic representation
ISSN号	2162-237X
DOI	10.1109/TNNLS.2018.2856096
通讯作者	Zhang, Chunjie(chunjie.zhang@ia.ac.cn)
英文摘要	Object-centric-based categorization methods have been proven more effective than hard partitions of images (e.g., spatial pyramid matching). However, how to determine the locations of objects is still an open problem. Besides, modeling of context areas is often mixed with the background. Moreover, the semantic information is often ignored by these methods that only use visual representations for classification. In this paper, we propose an object categorization method by semantically modeling the object and context information (SOC). We first select a number of candidate regions with high confidence scores and semantically represent these regions by measuring correlations of each region with prelearned classifiers (e.g., local feature-based classifiers and deep convolutional-neural-network-based classifiers). These regions are clustered for object selections. The other selected areas are then viewed as context areas. We treat other areas beyond the object and context areas within one image as the background. The visually and semantically represented objects and contexts are then used along with the background area for object representations and categorizations. Experimental results on several public data sets well demonstrate the effectiveness of the proposed object categorization method by semantically modeling the object and context information.
资助项目	Scientific Research Key Program of Beijing Municipal Commission of Education[KZ201610005012] ; National Science Foundation of China[61429201] ; ARO[W911NF-15-1-0290] ; NEC Laboratories of America ; Blippar
WOS关键词	IMAGE CLASSIFICATION ; LOW-RANK ; REPRESENTATION
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000461854100004
资助机构	Scientific Research Key Program of Beijing Municipal Commission of Education ; National Science Foundation of China ; ARO ; NEC Laboratories of America ; Blippar
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/28059]
专题	中国科学院自动化研究所
通讯作者	Zhang, Chunjie
作者单位	1.Chinese Acad Sci, Res Ctr Brain Inspired Intelligence, Inst Automat, 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 100190, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China 5.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,Tian, Qi. Semantically Modeling of Object and Context for Categorization[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2019,30(4):1013-1024.
APA	Zhang, Chunjie,Cheng, Jian,&Tian, Qi.(2019).Semantically Modeling of Object and Context for Categorization.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,30(4),1013-1024.
MLA	Zhang, Chunjie,et al."Semantically Modeling of Object and Context for Categorization".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 30.4(2019):1013-1024.