Cross-view action recognition by cross-domain learning

作者：

Highlights：

• We proposed a novel cross-domain learning method to handle action recognition.

• We applied the block-wise weighted kernel function to leverage cross-view information.

• We evaluated the proposed method on two popular cross-view human action datasets.

摘要

•We proposed a novel cross-domain learning method to handle action recognition.•We applied the block-wise weighted kernel function to leverage cross-view information.•We evaluated the proposed method on two popular cross-view human action datasets.

论文关键词：Cross-domain,Human action recognition,Action classifier

论文评审过程：Received 16 August 2015, Revised 2 April 2016, Accepted 24 April 2016, Available online 30 April 2016, Version of Record 10 November 2016.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.04.011