Knowing Verb From Object: Retagging With Transfer Learning on Verb-Object Concept Images

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Knowing Verb From Object: Retagging With Transfer Learning on Verb-Object Concept Images
	Sun, Chao; Bao, Bing-Kun; Xu, Changsheng
刊名	IEEE TRANSACTIONS ON MULTIMEDIA
	2015-10-01
卷号	17 期号:10 页码:1747-1759
关键词	Bayesian retagging verb-object image
英文摘要	Image retagging is significant and essential for tag-based applications, such as search and browsing. However, most existing image retagging approaches are typically based on enriching-and-removing and/or reranking strategies, which lead to two drawbacks: 1) since the object and/or human appeared in the images are tagged as individuals, the meanings represented by the mutual context of object and human are ignored and not tagged, and 2) some images which are visually dissimilar but semantically similar could be filtered incorrectly, as they are conflict with the content consistency rule. These two defects are distinct especially when images with human-object interactions are retagged. To tackle these defects, in this paper we propose a Bayesian approach to jointly consider the human and object in an image and retag it properly. In our approach, human and objects in images are detected and their interrelationships are taken into account. Tags which represent the mutual context of human and objects are then mapped to those interrelationships by a probabilistic graphical model. For a new image which lacks the tag representing the interaction between human and object, our model can correctly retag it for the interaction. In this paper, those images involving human-object interactions are called verb-object concept images, and experiments on a 60-class dataset demonstrate the capacity of our Bayesian retagging approach of verb-object concept images (BRVOI).
WOS标题词	Science & Technology ; Technology
类目[WOS]	Computer Science, Information Systems ; Computer Science, Software Engineering ; Telecommunications
研究领域[WOS]	Computer Science ; Telecommunications
关键词[WOS]	CONTEXT ; MODELS
收录类别	SCI
语种	英语
WOS记录号	WOS:000361685400006
公开日期	2015-12-24
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/9019]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Sun, Chao,Bao, Bing-Kun,Xu, Changsheng. Knowing Verb From Object: Retagging With Transfer Learning on Verb-Object Concept Images[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2015,17(10):1747-1759.
APA	Sun, Chao,Bao, Bing-Kun,&Xu, Changsheng.(2015).Knowing Verb From Object: Retagging With Transfer Learning on Verb-Object Concept Images.IEEE TRANSACTIONS ON MULTIMEDIA,17(10),1747-1759.
MLA	Sun, Chao,et al."Knowing Verb From Object: Retagging With Transfer Learning on Verb-Object Concept Images".IEEE TRANSACTIONS ON MULTIMEDIA 17.10(2015):1747-1759.