Hierarchical deep semantic representation for visual categorization

doi:10.1016/j.neucom.2016.11.065

	Hierarchical deep semantic representation for visual categorization
	Zhang, Chunjie 1,2; Li, Ruiying 2; Huang, Qingming 2,3; Tian, Qi 4
	2017-09-27
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
卷号	257 页码:88-96
摘要	Visual features are unsatisfactory to effectively describe the visual semantics. However, single layer based semantic modeling may be not able to cope with complicated semantic contents. In this paper, we propose Hierarchical Deep Semantic Representation (H-DSR), a hierarchical framework which combines semantic context modeling with visual features. First, the input image is sampled with spatially fixed grids. Deep features are then extracted for each sample in particular location. Second, using pre-learned classifiers, a detection response map is constructed for each patch. Semantic representation is then extracted from the map, which have a sense of latent semantic context. We combine the semantic and visual representations for joint representation. Third, a hierarchical deep semantic representation is built with recurrent reconstructions using three layers. The concatenated visual and semantic representations are used as the inputs of subsequent layers for semantic representation extraction. Finally, we verify the effectiveness of H-DSR for visual categorization on two publicly available datasets: Oxford Flowers 17 and UIUC-Sports. Improved performances are obtained over many baseline methods. (C) 2017 Elsevier B.V. All rights reserved.
关键词	Semantic representation Visual categorization Image representation
DOI	10.1016/j.neucom.2016.11.065
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61303154] ; National Natural Science Foundation of China[61332016] ; National Basic Research Program of China (973 Program)[2012CB316400] ; National Basic Research Program of China (973 Program)[2015CB351802]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000404319800010
出版者	ELSEVIER SCIENCE BV
引用统计	被引频次：11[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/7083
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Huang, Qingming
作者单位	1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Key Lab Intell Info Proc, Beijing 100190, Peoples R China 4.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
推荐引用方式 GB/T 7714	Zhang, Chunjie,Li, Ruiying,Huang, Qingming,et al. Hierarchical deep semantic representation for visual categorization[J]. NEUROCOMPUTING,2017,257:88-96.
APA	Zhang, Chunjie,Li, Ruiying,Huang, Qingming,&Tian, Qi.(2017).Hierarchical deep semantic representation for visual categorization.NEUROCOMPUTING,257,88-96.
MLA	Zhang, Chunjie,et al."Hierarchical deep semantic representation for visual categorization".NEUROCOMPUTING 257(2017):88-96.