Feature coding via vector difference for image classification

Xin Zhao, Yinan Yu, Yongzhen Huang, Kaiqi Huang, Tieniu TanICIP 2012 · OpenReview

Abstract

An 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.
BibTeX
@inproceedings{zhao2012feature,
  author = {Xin Zhao and Yinan Yu and Yongzhen Huang and Kaiqi Huang and Tieniu Tan},
  title = {{Feature coding via vector difference for image classification}},
  booktitle = {ICIP},
  year = {2012},
  url = {https://openreview.net/forum?id=7e6eHgt8zs},
}

Loading related content...

Figure