LSH-based semantic dictionary learning for large scale image understanding

doi:10.1016/j.jvcir.2015.06.008

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	LSH-based semantic dictionary learning for large scale image understanding
	Li, Liang 1; Yan, Chenggang Clarence 2; Ji, Wen 3; Chen, Bo-Wei 4; Jiang, Shuqiang 3; Huang, Qingming 1,3
刊名	JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
	2015-08-01
卷号	31 页码:231-236
关键词	Locality sensitive hashing Online dictionary learning Spatial pyramid matching Image understanding
ISSN号	1047-3203
DOI	10.1016/j.jvcir.2015.06.008
英文摘要	Large scale image understanding is a challenging but significant task to comprehend image contents on the internet. The de-facto standard methods based on machine learning or computer vision still suffer from a phenomenon of visual polysemia and concept polymorphism (VPCP). To resolve the VPCP, semantic dictionary has been proposed to characterize the membership distribution between visual appearances and semantic concepts. In this paper, we propose an online semantic dictionary learning algorithm on the base of both locality sensitive hashing (LSH) and stochastic approximations, which can scale up to large scale datasets with millions of training samples and speedup the efficiency of follow-up processing. With the help of the LSH-based semantic dictionary, we develop an extension of the spatial pyramid matching (SPM) kernel method by generalizing the dictionary as a basic semantic description. The efficiency of our approach is validated in the experiments of web-scale semantic image search and image classification on the ImageNet dataset and Caltech-256 dataset. (C) 2015 Published by Elsevier Inc.
资助项目	National Basic Research Program of China (973 Program)[2012CB316400] ; National Basic Research Program of China (973 Program)[2015CB351802] ; National 275 Natural Science Foundation of China[61332016] ; National 275 Natural Science Foundation of China[61025011] ; National 275 Natural Science Foundation of China[61402431] ; National 275 Natural Science Foundation of China[61472203] ; China Postdoctoral Science Foundation
WOS研究方向	Computer Science
语种	英语
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
WOS记录号	WOS:000359181600021
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/9483]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Yan, Chenggang Clarence
作者单位	1.Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing, Peoples R China 2.Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 4.Princeton Univ, Dept Elect Engn, Princeton, NJ 08544 USA
推荐引用方式 GB/T 7714	Li, Liang,Yan, Chenggang Clarence,Ji, Wen,et al. LSH-based semantic dictionary learning for large scale image understanding[J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,2015,31:231-236.
APA	Li, Liang,Yan, Chenggang Clarence,Ji, Wen,Chen, Bo-Wei,Jiang, Shuqiang,&Huang, Qingming.(2015).LSH-based semantic dictionary learning for large scale image understanding.JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,31,231-236.
MLA	Li, Liang,et al."LSH-based semantic dictionary learning for large scale image understanding".JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 31(2015):231-236.