TY - GEN
T1 - Learning sparse covariance patterns for natural scenes
AU - Wang, Liwei
AU - Li, Yin
AU - Jia, Jiaya
AU - Sun, Jian
AU - Wipf, David
AU - Rehg, James M.
PY - 2012
Y1 - 2012
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84866645939&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866645939&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2012.6248000
DO - 10.1109/CVPR.2012.6248000
M3 - Conference contribution
AN - SCOPUS:84866645939
SN - 9781467312264
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2767
EP - 2774
BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Y2 - 16 June 2012 through 21 June 2012
ER -