ML Anthology

Learning Sparse Covariance Patterns for Natural Scenes

Liwei Wang, Yin Li, Jiaya Jia, Jian Sun, David P. Wipf, James M. Rehg
CVPR 2012 pp. 2767-2774
doi:10.1109/CVPR.2012.6248000 /cvpr/2012/wang2012cvpr-learning/

Abstract

For scene classification, patch-level linear features do not always work as well as handcrafted features. In this paper, we present a new model to greatly improve the usefulness of linear features in classification by introducing co-variance patterns. We analyze their properties, discuss the fundamental importance, and present a generative model to properly utilize them. With this set of covariance information, in our framework, even the most naive linear features that originally lack the vital ability in classification become powerful. Experiments show that the performance of our new covariance model based on linear features is comparable with or even better than handcrafted features in scene classification. © 2012 IEEE.

PDF CVPR Semantic Scholar

Cite

Text

Wang et al. "Learning Sparse Covariance Patterns for Natural Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6248000

Markdown

[Wang et al. "Learning Sparse Covariance Patterns for Natural Scenes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/wang2012cvpr-learning/) doi:10.1109/CVPR.2012.6248000

BibTeX

@inproceedings{wang2012cvpr-learning,
  title     = {{Learning Sparse Covariance Patterns for Natural Scenes}},
  author    = {Wang, Liwei and Li, Yin and Jia, Jiaya and Sun, Jian and Wipf, David P. and Rehg, James M.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {2767-2774},
  doi       = {10.1109/CVPR.2012.6248000},
  url       = {https://mlanthology.org/cvpr/2012/wang2012cvpr-learning/}
}