CASIA OpenIR  > 类脑智能研究中心
Incremental Codebook Adaptation for Visual Representation and Categorization
Zhang CJ(张淳杰); Cheng J(程健); Tian Q(田奇)
2017
发表期刊IEEE Transactions on Cybernetics
期号0页码:0
摘要The bag-of-visual-words model is widely used for visual content analysis. For visual data, the codebook plays an important role for efficient representation. However, the codebook has to be re-learned with the changes of training images. Once the codebook is changed, the encoding parameters of local features have to be re-computed. To alleviate this problem, in this paper, we propose an incremental codebook adaptation method for efficient visual representation. Instead of learning a new codebook, we gradually adapt a pre-learned codebook using new images in an incremental way. To make use of the pre-learned codebook, we try to make changes to the pre-learned codebook with sparsity constraint and low-rank correlation. Besides, we also encode visually similar local features within a neighborhood to take advantage of locality information and ensure the encoded parameters are consistent. To evaluate the effectiveness of the proposed method, we apply the proposed method for categorization tasks on several public image datasets. Experimental results prove the effectiveness and usefulness of the proposed method over other codebook based methods.
关键词Codebook Learning Visual Representation Low-rank Sparse Coding
DOI10.1109/TCYB.2017.2726079
WOS记录号WOS:000435342100006
引用统计
被引频次:4[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/15319
专题类脑智能研究中心
作者单位1.Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China
2.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China.
3.Department of Computer Sciences, University of Texas at San Antonio. TX, 78249-1604, U.S.A.
推荐引用方式
GB/T 7714
Zhang CJ,Cheng J,Tian Q. Incremental Codebook Adaptation for Visual Representation and Categorization[J]. IEEE Transactions on Cybernetics,2017(0):0.
APA Zhang CJ,Cheng J,&Tian Q.(2017).Incremental Codebook Adaptation for Visual Representation and Categorization.IEEE Transactions on Cybernetics(0),0.
MLA Zhang CJ,et al."Incremental Codebook Adaptation for Visual Representation and Categorization".IEEE Transactions on Cybernetics .0(2017):0.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
07990530.pdf(2354KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 请求全文
t-cyber 录用邮件.pdf(130KB) 开放获取--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 CJ(张淳杰)]的文章
[Cheng J(程健)]的文章
[Tian Q(田奇)]的文章
百度学术
百度学术中相似的文章
[Zhang CJ(张淳杰)]的文章
[Cheng J(程健)]的文章
[Tian Q(田奇)]的文章
必应学术
必应学术中相似的文章
[Zhang CJ(张淳杰)]的文章
[Cheng J(程健)]的文章
[Tian Q(田奇)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 07990530.pdf
格式: Adobe PDF
文件名: t-cyber 录用邮件.pdf
格式: Adobe PDF
此文件暂不支持浏览
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。