Zhiwu Huang, Chengde Wan, Thomas Probst, Luc Van Gool
TL;DR本文提出了一种基于深度学习的骨骼动作识别方法,采用了 Lie 群结构,并设计了旋转映射和对数映射层,以学习更合适的特征,并在标准的 3D 人体动作识别数据集上取得了优异的性能。
Abstract
In recent years, skeleton-based action recognition has become a popular 3D
classification problem. State-of-the-art methods typically first represent each
motion sequence as a high-dimensional trajectory on a Lie group with an
additional dynamic time warping, and then shallowly learn f