A sample-based hierarchical adaptive K-means clustering method for large-scale video retrieval

作者：

Highlights：

• The multilevel random sampling strategy is employed to handle large datasets.

• The adaptive K-means algorithm is utilized to improve the quality of clusters.

• The fast label scheme is used to assign data to the closest cluster efficiently.

摘要

•The multilevel random sampling strategy is employed to handle large datasets.•The adaptive K-means algorithm is utilized to improve the quality of clusters.•The fast label scheme is used to assign data to the closest cluster efficiently.

论文关键词：Data clustering,K-means algorithm,Pattern recognition,Content-based video copy detection,Large-scale data

论文评审过程：Received 22 July 2012, Revised 1 May 2013, Accepted 7 May 2013, Available online 20 May 2013.

论文官网地址：https://doi.org/10.1016/j.knosys.2013.05.003