Multiview Label Sharing for Visual Representations and Classifications

doi:10.1109/TMM.2017.2759500

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 图像与视频分析团队

	Multiview Label Sharing for Visual Representations and Classifications
	Zhang, Chunjie1,2 ; Cheng, Jian2,3,4 ; Tian, Qi 5
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2018-04-01
卷号	20 期号:4 页码:903-913
关键词	Multi-view Learning Linear Transformation Shared Space Image Representation Visual Classification
DOI	10.1109/TMM.2017.2759500
文献子类	Article
英文摘要	Different views represent different aspects of images. It is more effective to combine them for visual classifications. This paper proposes a novel multiview label sharing method to combine the discriminative power of different views for classifications. Especially, we linearly transfer different views into a shared space for representations. The inter-view similarities are kept in the shared space for each view. We also ensure the intra-view similarities of the same class between different views are preserved in the shared space. We jointly learn the classifiers and transformation matrices by minimizing the summed classification loss along with the inter-view and intra-view similarity constraints. In this paper, the inter-view constraints refer to the similarities between images of the corresponding view, whereas the intra-view constraints refer to the similarities between different views of images with the same semantics. Experimental results and analysis on several public datasets show the effectiveness of the proposed multiview label sharing method for visual classifications.
WOS关键词	IMAGE CLASSIFICATION ; LOW-RANK ; SPARSE DECOMPOSITION
WOS研究方向	Computer Science ; Telecommunications
语种	英语
WOS记录号	WOS:000427623000011
资助机构	National Natural Science Foundation of China(61303154 ; Scientific Research Key Program of Beijing Municipal Commission of Education(KZ201610005012) ; ARO Grant(W911NF-15-1-0290) ; NEC Laboratories of America ; Blippar ; National Science Foundation of China(61429201) ; 61332016)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/21991]
专题	自动化研究所_模式识别国家重点实验室_图像与视频分析团队
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, Natl Lab Pattern Recognit, Inst Automat, 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. Multiview Label Sharing for Visual Representations and Classifications[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2018,20(4):903-913.
APA	Zhang, Chunjie,Cheng, Jian,&Tian, Qi.(2018).Multiview Label Sharing for Visual Representations and Classifications.IEEE TRANSACTIONS ON MULTIMEDIA,20(4),903-913.
MLA	Zhang, Chunjie,et al."Multiview Label Sharing for Visual Representations and Classifications".IEEE TRANSACTIONS ON MULTIMEDIA 20.4(2018):903-913.