Unsupervised video categorization based on multivariate information bottleneck method

作者：

Highlights：

• Novel multivariate IB model is proposed for unsupervised video categorization.

• Effective solution is designed to integrate multiple features simultaneously.

• Information-theoretic optimization is constructed to alleviate the semantic gap.

摘要

•Novel multivariate IB model is proposed for unsupervised video categorization.•Effective solution is designed to integrate multiple features simultaneously.•Information-theoretic optimization is constructed to alleviate the semantic gap.

论文关键词：Video categorization,Unsupervised learning,Multivariate information bottleneck,Multiple features,Mutual information

论文评审过程：Received 18 June 2014, Revised 23 March 2015, Accepted 28 March 2015, Available online 3 April 2015, Version of Record 13 May 2015.

论文官网地址：https://doi.org/10.1016/j.knosys.2015.03.028