-
[show abstract]
[hide abstract]
ABSTRACT: A new framework for high-level feature extraction (or semantic concept detection) is proposed. In this system, features at different granularities are extracted, and four classifiers with complementary features for each concept are employed, and then the results are fused. We have evaluated 18 fusion schemes, and choose the best one for each concept to form the final results. The experiments on the auto-test corpus and TRECVID-2008 corpus show that the proposed system is effective and stable.
Industrial Electronics and Applications, 2009. ICIEA 2009. 4th IEEE Conference on; 06/2009
-
Zan Gao,
Zhi-Cheng Zhao,
Tao Liu,
Xiaoming Nan,
Mei Mei,
Bin Zhang,
Xiaodan Liu,
Xu Peng,
Hui Zheng,
Yanyun Zhao,
Anni Cai
TRECVID 2008 workshop participants notebook papers, Gaithersburg, MD, USA, November 2008; 01/2008
-
[show abstract]
[hide abstract]
ABSTRACT: A great deal of region-related concept detection algorithms have been proposed so far, but there are few of them concerning about the problem of mismatched regions at training and testing stages. In order to investigate the mismatch problem in region-related concept detection, we introduce three kinds of methods to annotate the datasets, and then conduct experiments on differently annotated training and testing datasets. We find from these experiments that the detection performance is the best when the regions of a region-related concept are well defined and matched during training and testing, or the detection performance will be decreased. Based on these observations, we propose a fusion scheme to combine the results of classifiers trained with datasets which are annotated by different methods. Experiments on Trecvid-2007 test corpus show that the proposed fusion scheme can obtain performance improvement up to 6~12%.
Computational Intelligence and Natural Computing, International Conference on. 1:42-46.
