Deep correlation features for image style classification

Wei Ta Chu, Yi Ling Wu

研究成果: Conference contribution

23 引文 斯高帕斯(Scopus)

摘要

This paper presents a comprehensive study of deep correlation features on image style classification. Inspired by that correlation between feature maps can effectively describe image texture, we design and transform various such correlations into style vectors, and investigate classification performance brought by different variants. In addition to intra-layer correlation, we also propose inter-layer correlation and verify its benefit. Through extensive experiments on image style classification and artist classification, we demonstrate that the proposed style vectors significantly outperforms CNN features coming from fully-connected layers, as well as outperforms the state-of-the-art deep representation.

原文English
主出版物標題MM 2016 - Proceedings of the 2016 ACM Multimedia Conference
發行者Association for Computing Machinery, Inc
頁面402-406
頁數5
ISBN(電子)9781450336031
DOIs
出版狀態Published - 2016 十月 1
事件24th ACM Multimedia Conference, MM 2016 - Amsterdam, United Kingdom
持續時間: 2016 十月 152016 十月 19

出版系列

名字MM 2016 - Proceedings of the 2016 ACM Multimedia Conference

Conference

Conference24th ACM Multimedia Conference, MM 2016
國家United Kingdom
城市Amsterdam
期間16-10-1516-10-19

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Software

指紋 深入研究「Deep correlation features for image style classification」主題。共同形成了獨特的指紋。

引用此