CASIA OpenIR
Name-face association with web facial image supervision
Chen, Zhineng1; Zhang, Wei2; Deng, Bin3; Xie, Hongtao2; Gu, Xiaoyan2
Source PublicationMULTIMEDIA SYSTEMS
ISSN0942-4962
2019-02-01
Volume25Issue:1Pages:1-20
Corresponding AuthorXie, Hongtao(xiehongtao@iie.ac.cn)
AbstractThis paper describes methods for automatically associating faces detected from multimedia documents with their names presented in the surrounding metadata. We consider the task in the image matching (IM) framework, where external Web facial images are automatically retrieved as the gallery face set of the names in advance, and a detected face is assigned to one of the names, or none of them, according to the association score between the two kinds of faces and constraints. Several important issues are investigated within the IM framework. In collecting Web facial images, beyond the basic scheme that use a celebrity name purely as the query to crawl facial images, a context-assisted image search method is proposed to enhance the relevance and discriminability of the retrieved faces. In constraint formulation, we propose an assigning-thresholding (AT) pipeline to uniformly ensure that the name-face correspondence is strictly one-to-one, and set low confidence associations as null assignments. In association score computation, we propose methods that jointly consider IM with the well-established graph-based association (GA) method at different stages, aiming at producing more accurate scores to benefit the association. Based on these efforts, an Accu-IM method performing the association as accurate as possible and a Fast-IM method performing the association in real-time are respective proposed. Extensive experiments on datasets of captioned News images and Web videos both demonstrate the advantages of the proposed efforts individually and jointly, which consistently provide improvement gains under different settings when compared with state-of-the-art methods.
KeywordName-face association Image matching Multimedia fusion Web facial images Weakly supervised
DOI10.1007/s00530-017-0544-y
WOS KeywordRECOGNITION ; ANNOTATION ; IDENTIFICATION ; VERIFICATION ; DISCOVERY ; SCHEME ; VIDEOS ; MOVIE
Indexed BySCI
Language英语
Funding ProjectNational Nature Science Foundation of China[61303175] ; National Nature Science Foundation of China[61303171] ; National Nature Science Foundation of China[61602463]
Funding OrganizationNational Nature Science Foundation of China
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems ; Computer Science, Theory & Methods
WOS IDWOS:000459419800001
PublisherSPRINGER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/25009
Collection中国科学院自动化研究所
Corresponding AuthorXie, Hongtao
Affiliation1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Informat Engn, Beijing 100093, Peoples R China
3.Hunan Univ Technol, Sch Comp Sci, Zhuzhou 412007, Hunan, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Chen, Zhineng,Zhang, Wei,Deng, Bin,et al. Name-face association with web facial image supervision[J]. MULTIMEDIA SYSTEMS,2019,25(1):1-20.
APA Chen, Zhineng,Zhang, Wei,Deng, Bin,Xie, Hongtao,&Gu, Xiaoyan.(2019).Name-face association with web facial image supervision.MULTIMEDIA SYSTEMS,25(1),1-20.
MLA Chen, Zhineng,et al."Name-face association with web facial image supervision".MULTIMEDIA SYSTEMS 25.1(2019):1-20.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen, Zhineng]'s Articles
[Zhang, Wei]'s Articles
[Deng, Bin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, Zhineng]'s Articles
[Zhang, Wei]'s Articles
[Deng, Bin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, Zhineng]'s Articles
[Zhang, Wei]'s Articles
[Deng, Bin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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