CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Birds of a feather flock together: Visual representation with scale and class consistency
Zhang, Chunjie1,2; Li, Chenghua3; Lu, Dongyuan4; Cheng, Jian1,2,3,5; Tian, Qi6

There are three problems with a local-feature based representation scheme. First, local regions are often densely extracted or determined through detection without considering the scales of local regions. Second, local features are encoded separately, leaving the relationship among them unconsidered. Third, local features are simply encoded without considering the class information. To solve these problems, in this paper, we propose a scale and class consistent local-feature encoding method for image representation, which is achieved through the dense extraction of local features in different scale spaces, and the subsequent learning of the encoding parameters. In addition, instead of encoding each local feature independently, we jointly optimize the encoding parameters of the local features. Moreover, we also impose class consistency during the local-feature encoding process. We test the discriminative power of image representations on image classification tasks. Experiments on several public image datasets demonstrate that the proposed method achieves a superior performance compared with many other local-feature based methods. (C) 2018 Elsevier Inc. All rights reserved.

KeywordScale Consistency Discriminative Sparse Coding Class Consistency Image Classification
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding OrganizationNational Natural Science Foundation of China(61303154 ; Scientific Research Key Program of Beijing Municipal Commission of Education(KZ201610005012) ; ARO grant(W911NF-15-1-0290) ; Blippar ; National Science Foundation of China (NSFC)(61429201) ; NEC Laboratories America ; 61332016)
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems
WOS IDWOS:000441494000008
Citation statistics
Cited Times:6[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Affiliation1.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100080, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, POB 2728, Beijing, Peoples R China
4.Univ Int Business & Econ, Sch Informat Technol & Management, Beijing 100029, Peoples R China
5.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing, Peoples R China
6.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Zhang, Chunjie,Li, Chenghua,Lu, Dongyuan,et al. Birds of a feather flock together: Visual representation with scale and class consistency[J]. INFORMATION SCIENCES,2018,460(460-461):115-127.
APA Zhang, Chunjie,Li, Chenghua,Lu, Dongyuan,Cheng, Jian,&Tian, Qi.(2018).Birds of a feather flock together: Visual representation with scale and class consistency.INFORMATION SCIENCES,460(460-461),115-127.
MLA Zhang, Chunjie,et al."Birds of a feather flock together: Visual representation with scale and class consistency".INFORMATION SCIENCES 460.460-461(2018):115-127.
Files in This Item: Download All
File Name/Size DocType Version Access License
1-s2.0-S002002551631(2229KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Chunjie]'s Articles
[Li, Chenghua]'s Articles
[Lu, Dongyuan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Chunjie]'s Articles
[Li, Chenghua]'s Articles
[Lu, Dongyuan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Chunjie]'s Articles
[Li, Chenghua]'s Articles
[Lu, Dongyuan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 1-s2.0-S0020025516315560-main.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.