CASIA OpenIR  > 类脑智能研究中心
Bundled local features for image representation
Zhang CJ(张淳杰); Sang JT(桑基韬); Zhu GB(朱桂波); Tian Q(田奇)
2017
发表期刊IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
期号0页码:0
摘要Local features have been widely used for image representation. Traditional methods often treat each local feature independently or simply model the correlations of local features with spatial partition. However, local features are correlated and should be jointly modeled. Besides, due to the variety of images, pre-defined partition rules will probably introduce noisy information. To solve these problems, in this paper, we propose a novel bundled local features method for efficient image representation and apply it for classification. Specially, we first extract local features and bundle them together with over-complete spatial shapes by viewing each local feature as the central point. Then, the most discriminatively bundling features are selected by reconstruction error minimization. The encoding parameters are then used for image representations in a matrix form. Finally, we train bi-linear classifiers with quadratic hinge loss to predict the classes of images. The proposed method can combine local features appropriately and efficiently for discriminative representations. Experimental results on three image datasets show the effectiveness of the proposed method compared with other local features combination strategies.
关键词Bundled Features Image Representation Image Classification Codebook Feature Selection
DOI10.1109/TCSVT.2017.2694060
引用统计
被引频次:3[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/173211/15315
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, Beijing, China
2.School of Computer and Control Engineering, University of Chinese Academy of Sciences, 100049, Beijing, China
3.School of Computer and Information Technology, Beijing Jiaotong University
4.Department of Computer Sciences, University of Texas at San Antonio. TX, 78249, U.S.A.
推荐引用方式
GB/T 7714
Zhang CJ,Sang JT,Zhu GB,et al. Bundled local features for image representation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2017(0):0.
APA Zhang CJ,Sang JT,Zhu GB,&Tian Q.(2017).Bundled local features for image representation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY(0),0.
MLA Zhang CJ,et al."Bundled local features for image representation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY .0(2017):0.
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
07898795.pdf(1215KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
t-csvt 2 录用邮件.pdf(108KB) 开放获取--浏览 下载
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
[Sang JT(桑基韬)]的文章
[Zhu GB(朱桂波)]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
[Sang JT(桑基韬)]的文章
[Zhu GB(朱桂波)]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
[Sang JT(桑基韬)]的文章
[Zhu GB(朱桂波)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 07898795.pdf
格式: Adobe PDF
文件名: t-csvt 2 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。