CASIA OpenIR  > 模式识别国家重点实验室  > 图像与视频分析
Image Tag Refinement With View-Dependent Concept Representations
Fu, Jianlong1; Wang, Jinqiao1; Rui, Yong2; Wang, Xin-Jing2; Mei, Tao2; Lu, Hanqing1
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
2015-08-01
Volume25Issue:8Pages:1409-1422
SubtypeArticle
AbstractImage tag refinement is the task of refining initial tags of an image such that the refined tags can better reflect the content of the image and, therefore, can help users better access that image. The quality of tag refinement depends on the quality of concept representations that build a mapping from concepts to visual images. While good progress was made in the past decade on tag refinement, the previous approaches only achieved a limited success due to their limited concept representations. In this paper, we show that the visual appearances of a concept consist of both a generic view and a specific view, and therefore we can comprehensively represent a concept by two components. To ensure a clean concept representation, this representation is learned on clean click-through data, where noises are greatly reduced. In the framework, a coarse-to-fine image tag refinement is proposed, which: 1) first generates an efficient star graph to find candidate tags but missing in the initial tag list of an input image and 2) guided by this view-dependent concept representation, formulates a probabilistic objective function to eliminate irrelevant tags. Extensive experiments on two widely used standard data sets (MIRFlickr-25K and NUS-WIDE-270K) demonstrate the effectiveness of our approach.
KeywordConcept Representations Image Tag Refinement Image Tagging
WOS HeadingsScience & Technology ; Technology
WOS KeywordSEARCH ; RETRIEVAL ; RELEVANCE
Indexed BySCI
Language英语
WOS Research AreaEngineering
WOS SubjectEngineering, Electrical & Electronic
WOS IDWOS:000359213400012
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/8892
Collection模式识别国家重点实验室_图像与视频分析
Corresponding AuthorWang, Jinqiao
Affiliation1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Microsoft Res, Beijing 100080, Peoples R China
Recommended Citation
GB/T 7714
Fu, Jianlong,Wang, Jinqiao,Rui, Yong,et al. Image Tag Refinement With View-Dependent Concept Representations[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2015,25(8):1409-1422.
APA Fu, Jianlong,Wang, Jinqiao,Rui, Yong,Wang, Xin-Jing,Mei, Tao,&Lu, Hanqing.(2015).Image Tag Refinement With View-Dependent Concept Representations.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,25(8),1409-1422.
MLA Fu, Jianlong,et al."Image Tag Refinement With View-Dependent Concept Representations".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 25.8(2015):1409-1422.
Files in This Item: Download All
File Name/Size DocType Version Access License
Image Tag Refinement(3630KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Fu, Jianlong]'s Articles
[Wang, Jinqiao]'s Articles
[Rui, Yong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Fu, Jianlong]'s Articles
[Wang, Jinqiao]'s Articles
[Rui, Yong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Fu, Jianlong]'s Articles
[Wang, Jinqiao]'s Articles
[Rui, Yong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Image Tag Refinement with View-Dependent Concept Representations.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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