Inductive hierarchical nonnegative graph embedding for "verb-object" image classification

	Inductive hierarchical nonnegative graph embedding for "verb-object" image classification
	Sun, Chao 1,3; Bao, Bing-Kun2,3 ; Xu, Changsheng2,3
发表期刊	MACHINE VISION AND APPLICATIONS
	2014-10-01
卷号	25 期号:7 页码:1647-1659
文章类型	Article
摘要	Most existing image classification algorithms mainly focus on dealing with images with only "object" concepts. However, in real-world cases, a great variety of images contain "verb-object" concepts, rather than only "object" ones. The hierarchical structure embedded in these "verb-object" concepts can help to enhance classification. However, traditional feature representation methods cannot utilize it. To tackle this problem, we present in this paper a novel approach, called inductive hierarchical nonnegative graph embedding. By assuming that those "verb-object" concept images which share the same "object" part but different "verb" part have a specific hierarchical structure, we integrate this hierarchical structure into the nonnegative graph embedding technique, together with the definition of inductive matrix, to (1) conduct effective feature extraction from hierarchical structure, (2) easily transfer each new testing sample into its low-dimensional nonnegative representation, and (3) perform image classification of "verb-object" concept images. Extensive experiments compared with the state-of-the-art algorithms on nonnegative data factorization demonstrate the classification power of proposed approach on "verb-object" concept images classification.
关键词	Inductive Hierarchical Graph Embedding Verb-object
WOS标题词	Science & Technology ; Technology
关键词[WOS]	DIMENSIONALITY REDUCTION ; MATRIX FACTORIZATION ; IDENTIFICATION ; PARTS
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics ; Engineering, Electrical & Electronic
WOS记录号	WOS:000342435800003
引用统计	被引频次：2[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/173211/2868
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, Inst Automat, Natl Lab Pattern Recognit, Multimedia Comp Grp, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 3.China Singapore Inst Digital Media, Singapore, Singapore
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	Sun, Chao,Bao, Bing-Kun,Xu, Changsheng. Inductive hierarchical nonnegative graph embedding for "verb-object" image classification[J]. MACHINE VISION AND APPLICATIONS,2014,25(7):1647-1659.
APA	Sun, Chao,Bao, Bing-Kun,&Xu, Changsheng.(2014).Inductive hierarchical nonnegative graph embedding for "verb-object" image classification.MACHINE VISION AND APPLICATIONS,25(7),1647-1659.
MLA	Sun, Chao,et al."Inductive hierarchical nonnegative graph embedding for "verb-object" image classification".MACHINE VISION AND APPLICATIONS 25.7(2014):1647-1659.

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
Inductive hierarchic（1371KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载