A tensor-based deep learning framework

作者：

Highlights：

• We propose a novel deep learning model for action recognition.

• The deep learning model exploits multilinear algebra.

• The method derives spatio-temporal features.

摘要

•We propose a novel deep learning model for action recognition.•The deep learning model exploits multilinear algebra.•The method derives spatio-temporal features.

论文关键词：Deep learning,Hierarchical Temporal Memory (HTM),Tensor algebra,L1-norm,Support Vector Clustering,Spatio-temporal features

论文评审过程：Received 22 October 2013, Revised 9 May 2014, Accepted 4 August 2014, Available online 12 August 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.08.003