Exploring Relations of Visual Codes for Image Classification
Abstract
The classic Bag-of-Features (BOF) model and its extensional work use a single value to represent a visual code. This strategy ignores the relation of visual codes. In this paper, we explore this relation and propose a new algorithm for image classification. It consists of two main parts: 1) construct the codebook graph wherein a visual code is linked with other codes; 2) describe each local feature using a pair of related codes, corresponding to an edge of the graph. Our approach contains richer information than previous BOF models. Moreover, we demonstrate that these models are special cases of ours. Various coding and pooling algorithms can be embedded into our framework to obtain better performance. Experiments on different kinds of image classification databases demonstrate that our approach can stably achieve excellent performance compared with various BOF models.
Cite
Text
Huang et al. "Exploring Relations of Visual Codes for Image Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995655Markdown
[Huang et al. "Exploring Relations of Visual Codes for Image Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/huang2011cvpr-exploring/) doi:10.1109/CVPR.2011.5995655BibTeX
@inproceedings{huang2011cvpr-exploring,
title = {{Exploring Relations of Visual Codes for Image Classification}},
author = {Huang, Yongzhen and Huang, Kaiqi and Wang, Chong and Tan, Tieniu},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2011},
pages = {1649-1656},
doi = {10.1109/CVPR.2011.5995655},
url = {https://mlanthology.org/cvpr/2011/huang2011cvpr-exploring/}
}