Beyond Explicit Codebook Generation: Visual Representation Using Implicitly Transferred Codebooks
Zhang, Chunjie1,2; Cheng, Jian3; Liu, Jing3; Pang, Junbiao4; Huang, Qingming1,2,5; Tian, Qi6
2015-12-01
发表期刊IEEE TRANSACTIONS ON IMAGE PROCESSING
卷号24期号:12页码:5777-5788
文章类型Article
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.
关键词Codebook Transfer Image Representation Classification Reconstruction Sparse Constraint
WOS标题词Science & Technology ; Technology
DOI10.1109/TIP.2015.2485783
关键词[WOS]UNSUPERVISED DOMAIN ADAPTATION ; IMAGE CLASSIFICATION ; DICTIONARY ; KERNEL
收录类别SCI
语种英语
项目资助者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 Natural Science Foundation of China(61025011 ; ARO(W911NF-15-1-0290 ; Faculty Research Awards by NEC Laboratories of America ; 2015CB351802) ; 61170127 ; W911NF-12-1-0057) ; 61202234 ; 61272329 ; 61303154 ; 61332016 ; 61429201)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000369538200002
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/11338
专题模式识别国家重点实验室_图像与视频分析
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, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
4.Beijing Univ Technol, Coll Metropolitan Transportat, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100124, Peoples R China
5.Chinese Acad Sci, Inst Comp Technol, Key Lab Intell Info Proc, Beijing 100864, 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):5777-5788.
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),5777-5788.
MLA Zhang, Chunjie,et al."Beyond Explicit Codebook Generation: Visual Representation Using Implicitly Transferred Codebooks".IEEE TRANSACTIONS ON IMAGE PROCESSING 24.12(2015):5777-5788.
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
07286813.pdf(2652KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Chunjie]的文章
[Cheng, Jian]的文章
[Liu, Jing]的文章
百度学术
百度学术中相似的文章
[Zhang, Chunjie]的文章
[Cheng, Jian]的文章
[Liu, Jing]的文章
必应学术
必应学术中相似的文章
[Zhang, Chunjie]的文章
[Cheng, Jian]的文章
[Liu, Jing]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 07286813.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。