CASIA OpenIR  > 智能感知与计算研究中心
Feature Coding via Vector Difference for Image Classification
Zhao, Xin; Yu, Yinan; Huang, Yongzhen; Huang, Kaiqi; Tan, Tieniu
2012
Conference NameImage Processing (ICIP), 2012 19th IEEE International Conference on
Source PublicationIEEE
Conference Date2012
Conference PlaceUSA
AbstractAn effective image representation is important to an image classification task. The most popular image representation framework utilizes a feature coding algorithm to encode the extracted low-level feature descriptors into a vector representation. In this paper, we analyze the recently developed feature coding methods in a general way. According to their common characteristics, we propose a new coding scheme to perform feature coding based on the vector difference in a high-dimensional space which is obtained by explicit feature maps. As we illustrate, our method has promising results with small codebook sizes and generalizes most existing coding methods in a unified form.
KeywordImage Classification Feature Coding Vector Difference Additive Kernel
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12732
Collection智能感知与计算研究中心
Corresponding AuthorZhao, Xin
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
Zhao, Xin,Yu, Yinan,Huang, Yongzhen,et al. Feature Coding via Vector Difference for Image Classification[C],2012.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhao, Xin]'s Articles
[Yu, Yinan]'s Articles
[Huang, Yongzhen]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhao, Xin]'s Articles
[Yu, Yinan]'s Articles
[Huang, Yongzhen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhao, Xin]'s Articles
[Yu, Yinan]'s Articles
[Huang, Yongzhen]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.