Multi-View Image Classification With Visual, Semantic and View Consistency | |
Zhang, Chunjie5; Cheng, Jian2,3,4; Tian, Qi1 | |
刊名 | IEEE TRANSACTIONS ON IMAGE PROCESSING |
2020 | |
卷号 | 29页码:617-627 |
关键词 | Semantics Visualization Correlation Training Internet Encoding Image representation Multi-view learning image classification visual consistency semantic consistency view consistency |
ISSN号 | 1057-7149 |
DOI | 10.1109/TIP.2019.2934576 |
通讯作者 | Zhang, Chunjie(cjzhang@bjtu.edu.cn) |
英文摘要 | Multi-view visual classification methods have been widely applied to use discriminative information of different views. This strategy has been proven very effective by many researchers. On the one hand, images are often treated independently without fully considering their visual and semantic correlations. On the other hand, view consistency is often ignored. To solve these problems, in this paper, we propose a novel multi-view image classification method with visual, semantic and view consistency (VSVC). For each image, we linearly combine multi-view information for image classification. The combination parameters are determined by considering both the classification loss and the visual, semantic and view consistency. Visual consistency is imposed by ensuring that visually similar images of the same view are predicted to have similar values. For semantic consistency, we impose the locality constraint that nearby images should be predicted to have the same class by multi-view combination. View consistency is also used to ensure that similar images have consistent multi-view combination parameters. An alternative optimization strategy is used to learn the combination parameters. To evaluate the effectiveness of VSVC, we perform image classification experiments on several public datasets. The experimental results on these datasets show the effectiveness of the proposed VSVC method. |
资助项目 | Fundamental Research Funds for the Central Universities[2019RC040] ; National Science Foundation of China (NSFC)[61872362] ; Beijing Municipal Science and Technology Commission[Z181100008918012] |
WOS关键词 | LOW-RANK ; REPRESENTATION ; FEATURES |
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:000497434700027 |
资助机构 | Fundamental Research Funds for the Central Universities ; National Science Foundation of China (NSFC) ; Beijing Municipal Science and Technology Commission |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/29393] |
专题 | 类脑芯片与系统研究 |
通讯作者 | Zhang, Chunjie |
作者单位 | 1.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA 2.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 250014, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 250014, Peoples R China 5.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Chunjie,Cheng, Jian,Tian, Qi. Multi-View Image Classification With Visual, Semantic and View Consistency[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2020,29:617-627. |
APA | Zhang, Chunjie,Cheng, Jian,&Tian, Qi.(2020).Multi-View Image Classification With Visual, Semantic and View Consistency.IEEE TRANSACTIONS ON IMAGE PROCESSING,29,617-627. |
MLA | Zhang, Chunjie,et al."Multi-View Image Classification With Visual, Semantic and View Consistency".IEEE TRANSACTIONS ON IMAGE PROCESSING 29(2020):617-627. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论