Improved Shift Graph Convolutional Network for Action Recognition With Skeleton
Improved Shift Graph Convolutional Network for Action Recognition With Skeleton
复制标题
改进的移位图卷积网络在骨架动作识别中的应用
DOI：
10.1109/lsp.2023.3267975
复制
发表时间：
2023
影响因子：
3.9
通讯作者：
Chuankun Li;Shuai Li;Yanbo Gao;Lina Guo;Wanqing Li
中科院分区：
文献类型：
--
作者：
Chuankun Li;Shuai Li;Yanbo Gao;Lina Guo;Wanqing Li
移位图卷积网络（Shift-GCN）在基于骨架的动作识别方面取得了显著的成绩，且计算复杂度低于其他基于GCN的方法。然而，目前的shift - gcn采用一次空间位移、静态掩模和局部时间卷积，无法充分挖掘不同帧骨架关节之间的时空特征。为了解决这些问题，本文提出了一种改进的移位图卷积网络（shifft - gcn）。shifft - gcn算法由两个部分组成，一个是带动态掩模的双向空间位移图卷积，另一个是多尺度时间位移图卷积。双向空间移位图卷积利用了更多关节间的空间信息，动态掩模泛化能力更强，可以学习到不同关节间不同动作特征之间的不同相关性。多尺度时移图卷积通过多尺度卷积来补充位移特征，从而捕获更多的时间信息。此外，还采用了知识蒸馏的方法来降低计算复杂度。与Shift-GCN相比，本文提出的shifft - gcn在NTU-RGB+D和UAV-Human两种广泛使用的基准数据集上取得了更好的结果，计算复杂度更低。
Shift graph convolutional network (Shift-GCN) achieves remarkable performance for skeleton based action recognition with lower computational complexity than other GCN based methods. However, the current Shift-GCN, with one spatial shift, a static mask and a local temporal convolution, cannot fully explore the spatial-temporal features among skeleton joints of different frames. In order to address these problems, an improved shift graph convolutional network (Ishift-GCN) is proposed in this letter. The Ishift-GCN consists of two parts including a bidirectional spatial shift graph convolution with a dynamic mask, and a multi-scale temporal shift graph convolution. The bidirectional spatial shift graph convolution exploits more spatial information among joints, and the dynamic mask with stronger generalization ability can learn different correlations among features of different joints for different actions. The multi-scale temporal shift graph convolution captures more temporal information by complementing the shifted features with multi-scale convolution. Furthermore, knowledge distillation is used to reduce computational complexity. Compared with Shift-GCN, the proposed Ishift-GCN achieves better results with less computation complexity on two widely used benchmarks, namely the NTU-RGB+D and UAV-Human dataset.