Scalable and compact 3D action recognition with approximated RBF kernel machines

作者：

Highlights：

• Theoretically sound approximation of the Log-Euclidean kernel with an explicit feature map.

• Unbiased estimation with rapidly decreasing variance.

• Compact but effective representation in public benchmarks.

• Superior performance against state-of-the-art methods with respect to ease of training (minutes on CPU are enough, not hours of GPU computation as for deep learning methods).

摘要

•Theoretically sound approximation of the Log-Euclidean kernel with an explicit feature map.•Unbiased estimation with rapidly decreasing variance.•Compact but effective representation in public benchmarks.•Superior performance against state-of-the-art methods with respect to ease of training (minutes on CPU are enough, not hours of GPU computation as for deep learning methods).

论文关键词：Kernel machines,Kernel approximation,Action recognition,Skeletal joints,Covariance representation

论文评审过程：Received 17 July 2018, Revised 26 November 2018, Accepted 30 March 2019, Available online 4 April 2019, Version of Record 15 April 2019.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.03.031