A sample-based hierarchical adaptive K-means clustering method for large-scale video retrieval
A sample-based hierarchical adaptive K-means clustering method for large-scale video retrieval
复制标题
一种用于大规模视频检索的基于样本的分层自适应K均值聚类方法
DOI：
10.1016/j.knosys.2013.05.003
复制
发表时间：
2013-09
影响因子：
8.8
通讯作者：
Liu, Chaoteng
中科院分区：
文献类型：
--
作者：
Liao, Kaiyang;Liu, Guizhong;Xiao, Li;Liu, Chaoteng
Finding useful patterns in large datasets has attracted considerable interest recently, and one of the most widely studied problems in this area is the identification of clusters in a multi-dimensional dataset. This paper introduces a sample-based hierarchical adaptive K-means (SHAKM) clustering algorithm for large-scale video retrieval. To handle large databases efficiently, SHAKM employs a multilevel random sampling strategy. Furthermore, SHAKM utilises the adaptive K-means clustering algorithm to determine the correct number of clusters and to construct an unbalanced cluster tree. Furthermore, SHAKM uses the fast labelling scheme to assign each pattern in the dataset to the closest cluster. To evaluate the proposed method, several datasets are used to illustrate its effectiveness. The results show that SHAKM is fast and effective on very large datasets. Furthermore, the results demonstrate that the proposed method can be used efficiently and successfully for a project on content-based video copy detection.
登录
查看更多内容
k-Modes 聚类算法的相异性度量
影响因子：
8.8
作者：
Cao, Fuyuan;Liang, Jiye;Dang, Chuangyin
通讯作者：
Dang, Chuangyin
DOI：
10.1142/9789814343138_0001
发表时间：
1993-12
期刊：
--
影响因子：
--
作者：
R. Dubes
通讯作者：
R. Dubes
DOI：
10.1109/icnn.1994.374705
发表时间：
1994-06
期刊：
Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94)
影响因子：
--
作者：
J. Mao;Anil K. Jain
通讯作者：
J. Mao;Anil K. Jain
影响因子：
2.2
作者：
KOHONEN, T
通讯作者：
KOHONEN, T
影响因子：
7
作者：
J. Bezdek;R. Hathaway;J. Huband;C. Leckie;K. Ramamohanarao
通讯作者：
J. Bezdek;R. Hathaway;J. Huband;C. Leckie;K. Ramamohanarao