Abstract. Human action recognition based on skeleton currently has attracted a wide range of attention. The structure of skeleton data exists in the form of graph, thus most researchers use graph convolutional networks (GCN) to model skeleton sequences. However, the graph convolution network shares the same weight for all neighbor nodes and relies on the connection of graph edges. We introduce a method, a spatial–temporal graph attention networks (ST-GAT), to overcome the disadvantages of GCN. First, the ST-GAT defines the spatial–temporal neighbor nodes of the root node and the aggregation function through the attention mechanism. The adjacency matrix is only used in GAT to define related nodes, and the calculation of association weight is dependent on the feature expression of nodes. Then ST-GAT network attaches the obtained attention coefficient to each neighbor node to automatically learn the representation of spatiotemporal skeletal features and output the classification results. Extensive experiments on two challenging datasets consistently demonstrate the superiority of our method.

中文翻译：

---

用于基于骨架的动作识别的时空图注意网络

摘要。基于骨架的人体动作识别目前受到广泛关注。骨架数据的结构以图的形式存在，因此大多数研究人员使用图卷积网络（GCN）来对骨架序列进行建模。然而，图卷积网络对所有邻居节点共享相同的权重，并依赖于图边的连接。我们引入了一种方法，即时空图注意力网络（ST-GAT），以克服 GCN 的缺点。首先，ST-GAT 通过注意力机制定义了根节点的时空邻居节点和聚合函数。邻接矩阵仅在GAT中用于定义相关节点，关联权重的计算依赖于节点的特征表达。然后 ST-GAT 网络将获得的注意力系数附加到每个邻居节点上，自动学习时空骨骼特征的表示并输出分类结果。在两个具有挑战性的数据集上进行的大量实验一致证明了我们方法的优越性。