Image classification by search with explicitly and implicitly semantic representations

doi:10.1016/j.ins.2016.10.019

	Image classification by search with explicitly and implicitly semantic representations
	Zhang, Chunjie 1,2; Zhu, Guibo 3; Huang, Qingming 1,2,4; Tian, Qi 5
	2017-01-10
发表期刊	INFORMATION SCIENCES
ISSN	0020-0255
卷号	376 页码:125-135
摘要	Image classification refers to the task of automatically classifying the categories of images based on the contents. This task is typically solved using visual features with the histogram based classification scheme. Although effective, this strategy has two drawbacks. On one hand, histogram based representation often disregards the object layout which is very important for classification. On the other hand, visual features are unable to fully separate different images due to the semantic gap. To solve these two problems, in this paper, we propose a novel image classification method by explicitly and implicitly representing the images with searching strategy. First, to make use of object layouts, we randomly select a number of regions and then use these regions for image representations. Second, we generate the explicitly semantic representations using a number of pre-learned semantic models. Third, we measure the visual similarities with the Internet images and use the text information for implicitly semantic representations. Since Internet images are contaminated with noise, the resulting representations only implicitly reflect the contents of images. Finally, both the explicitly and implicitly semantic representations are jointly modeled for image classifications by training bi-linear classifiers. We evaluate the effectiveness of the proposed image classification by search with explicitly and implicitly semantic representations method (EISR) on the Scene-15 dataset, the MIT-Indoor dataset, the UIUC-Sports dataset and the PASCAL VOC 2007 dataset. The experimental results prove the usefulness of the proposed method. (C) 2016 Elsevier Inc. All rights reserved.
关键词	Explicit representation Implicit representation Semantic modeling Image classification
DOI	10.1016/j.ins.2016.10.019
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61303154]
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems
WOS记录号	WOS:000388545100009
出版者	ELSEVIER SCIENCE INC
引用统计	被引频次：24[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/2XEOYT63/7942
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhu, Guibo
作者单位	1.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100864, Peoples R China 3.Chinese Acad Sci, Inst Automat, Res Ctr Brain Inspired Intelligence, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Key Lab Intell Info Proc, Beijing 100190, Peoples R China 5.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
推荐引用方式 GB/T 7714	Zhang, Chunjie,Zhu, Guibo,Huang, Qingming,et al. Image classification by search with explicitly and implicitly semantic representations[J]. INFORMATION SCIENCES,2017,376:125-135.
APA	Zhang, Chunjie,Zhu, Guibo,Huang, Qingming,&Tian, Qi.(2017).Image classification by search with explicitly and implicitly semantic representations.INFORMATION SCIENCES,376,125-135.
MLA	Zhang, Chunjie,et al."Image classification by search with explicitly and implicitly semantic representations".INFORMATION SCIENCES 376(2017):125-135.