Action involves rich geometric and physical properties hidden in the spatial structure and temporal dynamics. However, there is a lack of synergy in investigating these properties and their joint embedding in the existing literature. In this paper, we propose a multi-derivative physical and geometric embedding network (PGEN) for action recognition from skeleton data. We model the skeleton joint and edge information using multi-derivative physical and geometric features. Then, a physical and geometric embedding network is proposed to learn co-occurrence features from joints and edges, respectively, and construct a unified convolutional embedding space, where the physical and geometric properties can be integrated effectively. Furthermore, we adopt a multi-task learning framework to explore the inter-dependencies between the physical and geometric properties of the action, which significantly improves the discrimination of the learned features. The experiments on the NTU RGB+D, NTU RGB+D 120, and SBU datasets demonstrate the effectiveness of our proposed representation and modeling method.

动作涉及隐藏在空间结构和时间动态中的丰富的几何和物理属性。但是，在研究这些特性及其联合嵌入现有文献中缺乏协同作用。在本文中，我们提出了一种多导数物理和几何嵌入网络（PGEN），用于从骨骼数据中识别动作。我们使用多导数物理和几何特征对骨骼关节和边缘信息进行建模。然后，提出一种物理和几何嵌入网络，分别从关节和边缘学习同现特征，并构建统一的卷积嵌入空间，从而可以有效地整合物理和几何属性。此外，我们采用了多任务学习框架来探索动作的物理和几何属性之间的相互依存关系，从而显着提高了对所学特征的辨别力。在NTU RGB + D，NTU RGB + D 120和SBU数据集上进行的实验证明了我们提出的表示和建模方法的有效性。