Improving Bag-of-Visual-Words model using visual n-grams for human action classification

作者：

Highlights：

• Visual n-grams for human action classification are introduced.

• A new version of Leader-Follower clustering improves the detection performance.

• Spatio-temporal relations are included using graphs from which n-grams are computed.

• Experimental results show its effectiveness to improve the Bag-of-Visual- Words.

摘要

•Visual n-grams for human action classification are introduced.•A new version of Leader-Follower clustering improves the detection performance.•Spatio-temporal relations are included using graphs from which n-grams are computed.•Experimental results show its effectiveness to improve the Bag-of-Visual- Words.

论文关键词：Bag-of-Visual-Words,Visual n-grams,Graph-based representation,Human action classification

论文评审过程：Received 19 April 2017, Revised 3 August 2017, Accepted 9 September 2017, Available online 11 September 2017, Version of Record 13 October 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.09.016