Folksonomy-Based Visual Ontology Construction and Its Applications

doi:10.1109/TMM.2016.2527602

	Folksonomy-Based Visual Ontology Construction and Its Applications
	Fang, Quan1 ; Xu, Changsheng1 ; Sang, Jitao1 ; Hossain, M. Shamim 2; Ghoneim, Ahmed 2,3
发表期刊	IEEE TRANSACTIONS ON MULTIMEDIA
	2016-04-01
卷号	18 期号:4 页码:702-713
文章类型	Article
摘要	An ontology hierarchically encodes concepts and concept relationships, and has a variety of applications such as semantic understanding and information retrieval. Previous work for building ontologies has primarily relied on labor-intensive human contributions or focused on text-based extraction. In this paper, we consider the problem of automatically constructing a folksonomy-based visual ontology (FBVO) from the user-generated annotated images. A systematic framework is proposed consisting of three stages as concept discovery, concept relationship extraction, and concept hierarchy construction. The noisy issues of the user-generated tags are carefully addressed to guarantee the quality of derived FBVO. The constructed FBVO finally consists of 139 825 concept nodes and millions of concept relationships by mining more than 2.4 million Flickr images. Experimental evaluations show that the derived FBVO is of high quality and consistent with human perception. We further demonstrate the utility of the derived FBVO in applications of complex visual recognition and exploratory image search.
关键词	Knowledge Discovery Ontology Visual Recognition
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TMM.2016.2527602
关键词[WOS]	CLASSIFICATION ; MULTIMEDIA ; SEMANTICS ; DATABASE ; ANNOTATION ; DETECTORS ; RETRIEVAL ; KNOWLEDGE ; IMAGES
收录类别	SCI
语种	英语
项目资助者	National Basic Research Program of China(2012CB316304) ; National Natural Science Foundation of China(61225009 ; Beijing Natural Science Foundation(4131004) ; Deanship of Scientific Research, King Saud University, Riyadh, Saudi Arabia(RGP-229) ; 61432019 ; 61332016 ; 61303176 ; U1435211)
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:000372790300012
引用统计	被引频次：31[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/173211/12192
专题	多模态人工智能系统全国重点实验室_多媒体计算
作者单位	1.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 100190, Peoples R China 2.King Saud Univ, Coll Comp & Informat Sci, Dept Software Engn, Riyadh 11543, Saudi Arabia 3.Menoufia Univ, Dept Comp Sci, Coll Sci, Menoufia 32721, Egypt
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Fang, Quan,Xu, Changsheng,Sang, Jitao,et al. Folksonomy-Based Visual Ontology Construction and Its Applications[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2016,18(4):702-713.
APA	Fang, Quan,Xu, Changsheng,Sang, Jitao,Hossain, M. Shamim,&Ghoneim, Ahmed.(2016).Folksonomy-Based Visual Ontology Construction and Its Applications.IEEE TRANSACTIONS ON MULTIMEDIA,18(4),702-713.
MLA	Fang, Quan,et al."Folksonomy-Based Visual Ontology Construction and Its Applications".IEEE TRANSACTIONS ON MULTIMEDIA 18.4(2016):702-713.

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
07403978.pdf（1067KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载