论文标题
KSHAPENET：基于骨架的肯德尔形状空间的Riemannian网络，以基于骨架的动作识别
KShapeNet: Riemannian network on Kendall shape space for Skeleton based Action Recognition
论文作者
论文摘要
深度学习体系结构（尽管在大多数计算机视觉任务中都取得成功）是为具有潜在欧几里得结构的数据而设计的，通常无法实现，因为预处理的数据可能位于非线性空间上。在本文中，我们提出了一种几何学意识到基于骨架的动作识别的深度学习方法。首先将骨骼序列建模为肯德尔形状空间上的轨迹，然后映射到线性切线空间。然后将所得的结构化数据馈送到深度学习体系结构，其中包括一层，该图层优化了3D骨架的刚性和非刚性变换，然后是CNN-LSTM网络。对两个大型骨骼数据集的评估，即NTU-RGB+D和NTU-RGB+D 120，已证明，提出的方法表现优于现有的几何深度学习方法，并且在最近发布的方法方面具有竞争力。
Deep Learning architectures, albeit successful in most computer vision tasks, were designed for data with an underlying Euclidean structure, which is not usually fulfilled since pre-processed data may lie on a non-linear space. In this paper, we propose a geometry aware deep learning approach for skeleton-based action recognition. Skeleton sequences are first modeled as trajectories on Kendall's shape space and then mapped to the linear tangent space. The resulting structured data are then fed to a deep learning architecture, which includes a layer that optimizes over rigid and non rigid transformations of the 3D skeletons, followed by a CNN-LSTM network. The assessment on two large scale skeleton datasets, namely NTU-RGB+D and NTU-RGB+D 120, has proven that proposed approach outperforms existing geometric deep learning methods and is competitive with respect to recently published approaches.
