Beyond Explicit Codebook Generation: Visual Representation Using Implicitly Transferred Codebooks

doi:10.1109/TIP.2015.2485783

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

	Beyond Explicit Codebook Generation: Visual Representation Using Implicitly Transferred Codebooks
	Zhang, Chunjie 2,3; Cheng, Jian 4; Liu, Jing 4; Pang, Junbiao 5; Huang, Qingming 1,2,3; Tian, Qi 6
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2015-12-01
卷号	24 期号:12 页码:12
关键词	Codebook transfer image representation classification reconstruction sparse constraint
ISSN号	1057-7149
DOI	10.1109/TIP.2015.2485783
英文摘要	The bag-of-visual-words model plays a very important role for visual applications. Local features are first extracted and then encoded to get the histogram-based image representation. To encode local features, a proper codebook is needed. Usually, the codebook has to be generated for each data set which means the codebook is data set dependent. Besides, the codebook may be biased when we only have a limited number of training images. Moreover, the codebook has to be pre-learned which cannot be updated quickly, especially when applied for online visual applications. To solve the problems mentioned above, in this paper, we propose a novel implicit codebook transfer method for visual representation. Instead of explicitly generating the codebook for the new data set, we try to make use of pre-learned codebooks using non-linear transfer. This is achieved by transferring the pre-learned codebooks with non-linear transformation and use them to reconstruct local features with sparsity constraints. The codebook does not need to be explicitly generated but can be implicitly transferred. In this way, we are able to make use of pre-learned codebooks for new visual applications by implicitly learning the codebook and the corresponding encoding parameters for image representation. We apply the proposed method for image classification and evaluate the performance on several public image data sets. Experimental results demonstrate the effectiveness and efficiency of the proposed method.
资助项目	Open Project through the Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences ; National Basic Research Program of China (973 Program)[2012CB316400] ; National Basic Research Program of China (973 Program)[2015CB351802] ; National Natural Science Foundation of China[61025011] ; National Natural Science Foundation of China[61170127] ; National Natural Science Foundation of China[61202234] ; National Natural Science Foundation of China[61272329] ; National Natural Science Foundation of China[61303154] ; National Natural Science Foundation of China[61332016] ; National Natural Science Foundation of China[61429201] ; ARO[W911NF-15-1-0290] ; ARO[W911NF-12-1-0057] ; Faculty Research Awards by NEC Laboratories of America
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000369538200002
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/8869]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhang, Chunjie
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intell Info Proc, Beijing 100864, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 100864, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 5.Beijing Univ Technol, Coll Metropolitan Transportat, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100124, Peoples R China 6.Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX 78249 USA
推荐引用方式 GB/T 7714	Zhang, Chunjie,Cheng, Jian,Liu, Jing,et al. Beyond Explicit Codebook Generation: Visual Representation Using Implicitly Transferred Codebooks[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2015,24(12):12.
APA	Zhang, Chunjie,Cheng, Jian,Liu, Jing,Pang, Junbiao,Huang, Qingming,&Tian, Qi.(2015).Beyond Explicit Codebook Generation: Visual Representation Using Implicitly Transferred Codebooks.IEEE TRANSACTIONS ON IMAGE PROCESSING,24(12),12.
MLA	Zhang, Chunjie,et al."Beyond Explicit Codebook Generation: Visual Representation Using Implicitly Transferred Codebooks".IEEE TRANSACTIONS ON IMAGE PROCESSING 24.12(2015):12.