Share Email Print
cover

Proceedings Paper

The application of graph diffusion in high-level feature extraction
Author(s): Xiaohan Du; Honggang Zhang; Jun Guo; Xiaojun Xu
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, a new graph diffusion method is presented to improve the high-level feature extraction performance. In this method, we construct a semantic graph by describe the concepts as nodes and the concept affinities as the weights of edges, then we use the training set and its corresponding label matrix to estimate the concept relationship, where the relationship of two concepts were measured by the inner product of its corresponding row vector. We test the method on the high-level feature extraction task of TRECVID 2009 and the experimental results show the effectiveness of the method.

Paper Details

Date Published: 13 March 2013
PDF: 5 pages
Proc. SPIE 8783, Fifth International Conference on Machine Vision (ICMV 2012): Computer Vision, Image Analysis and Processing, 87830M (13 March 2013); doi: 10.1117/12.2013805
Show Author Affiliations
Xiaohan Du, Beijing Univ. of Posts and Telecommunications (China)
Honggang Zhang, Beijing Univ. of Posts and Telecommunications (China)
Jun Guo, Beijing Univ. of Posts and Telecommunications (China)
Xiaojun Xu, Beijing Univ. of Posts and Telecommunications (China)


Published in SPIE Proceedings Vol. 8783:
Fifth International Conference on Machine Vision (ICMV 2012): Computer Vision, Image Analysis and Processing
Yulin Wang; Liansheng Tan; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top