Multiview Label Sharing for Visual Representations and Classifications
Zhang, Chunjie1,2; Cheng, Jian2,3,4; Tian, Qi5
发表期刊IEEE TRANSACTIONS ON MULTIMEDIA
2018-04-01
卷号20期号:4页码:903-913
文章类型Article
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.
关键词Multi-view Learning Linear Transformation Shared Space Image Representation Visual Classification
WOS标题词Science & Technology ; Technology
DOI10.1109/TMM.2017.2759500
关键词[WOS]IMAGE CLASSIFICATION ; LOW-RANK ; SPARSE DECOMPOSITION
收录类别SCI
语种英语
项目资助者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)
WOS研究方向Computer Science ; Telecommunications
WOS类目Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
WOS记录号WOS:000427623000011
引用统计
被引频次:24[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/21991
专题模式识别国家重点实验室_图像与视频分析
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
第一作者单位中国科学院自动化研究所
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
08059841.pdf(615KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Chunjie]的文章
[Cheng, Jian]的文章
[Tian, Qi]的文章
百度学术
百度学术中相似的文章
[Zhang, Chunjie]的文章
[Cheng, Jian]的文章
[Tian, Qi]的文章
必应学术
必应学术中相似的文章
[Zhang, Chunjie]的文章
[Cheng, Jian]的文章
[Tian, Qi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 08059841.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

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。