Action recognition by joint learning

作者：

Highlights：

• A novel middle-level representation is proposed based sparse coding.

• Jointly learning dictionary and MLR

• Results on YouTube action dataset and HMDB51 prove the effectiveness of our method.

摘要

•A novel middle-level representation is proposed based sparse coding.•Jointly learning dictionary and MLR•Results on YouTube action dataset and HMDB51 prove the effectiveness of our method.

论文关键词：Computer vision,Action recognition,Sparse coding,Multinomial logistic regression (MLR),Joint learning

论文评审过程：Received 18 September 2015, Revised 22 February 2016, Accepted 6 April 2016, Available online 15 April 2016, Version of Record 10 November 2016.

论文官网地址：https://doi.org/10.1016/j.imavis.2016.04.001