The application of graph diffusion in high-level feature extraction
Lists
Only you see this
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.
BibTeX
@inproceedings{du2013application,
author = {Xiaohan Du and Honggang Zhang and Jun Guo and Xiaojun Xu},
title = {{The application of graph diffusion in high-level feature extraction}},
booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
year = {2013},
doi = {10.1117/12.2013805},
}Loading related content...