A novel hierarchical framework for human action recognition

作者：

Highlights：

• We propose a hierarchical framework for 3D skeleton-based action recognition.

• We introduce a part-based feature vector to automatically cluster action sequences.

• We present a statistical principle to decide the time scale of motion features.

• Our method outperforms other state-of-the-art methods on the MSRAction3D dataset.

摘要

Highlights•We propose a hierarchical framework for 3D skeleton-based action recognition.•We introduce a part-based feature vector to automatically cluster action sequences.•We present a statistical principle to decide the time scale of motion features.•Our method outperforms other state-of-the-art methods on the MSRAction3D dataset.

论文关键词：Action recognition,3D skeleton,Hierarchical framework,Part-based,Time scale,Action graphs

论文评审过程：Received 3 July 2015, Revised 15 January 2016, Accepted 16 January 2016, Available online 30 January 2016, Version of Record 21 March 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.01.020