Learning sparse covariance patterns for natural scenes
Refereed conference paper presented and published in conference proceedings

替代計量分析
.

其它資訊
摘要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.
著者Wang L., Li Y., Jia J., Sun J., Wipf D., Rehg J.M.
會議名稱2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
會議開始日16.06.2012
會議完結日21.06.2012
會議地點Providence, RI
會議國家/地區美國
詳細描述organized by IEEE,
出版年份2012
月份10
日期1
頁次2767 - 2774
國際標準書號9781467312264
國際標準期刊號1063-6919
語言英式英語

上次更新時間 2020-29-10 於 00:29