Action recognition has wide applications in fields such as human–computer interaction, virtual reality, and robotics. Since human actions can be represented as a sequence of skeleton graphs, approaches based on graph neural networks (GNNs) have attracted considerable attention in the research action recognition. Recent studies have demonstrated the effectiveness of two-stream GNNs in which discriminative features for action recognition are extracted from both the joint stream and the bone stream. Each stream is generated by GNNs that support message passing along fixed connections between vertices. However, existing two-stream approaches have two limitations: no interaction is allowed between the two streams and temporary contacts between joints or bones cannot be modeled. To address these issues, we propose the interactive two-stream graph neural network, which employs a joint–bone communication block to accelerate the interaction between the joint stream and the bone stream. Furthermore, an adaptive strategy is introduced to enable dynamic connections between vertices. Extensive experiments on three large-scale datasets have demonstrated the effectiveness of our proposed method.

中文翻译：

---

用于基于骨架的动作识别的交互式双流图神经网络

动作识别在人机交互、虚拟现实、机器人等领域有着广泛的应用。由于人类动作可以表示为一系列骨架图，基于图神经网络（GNN）的方法在研究动作识别中引起了相当大的关注。最近的研究证明了双流 GNN 的有效性，其中从关节流和骨流中提取用于动作识别的判别特征。每个流都由 GNN 生成，这些 GNN 支持沿顶点之间的固定连接传递消息。然而，现有的双流方法有两个限制：两个流之间不允许交互，并且不能对关节或骨骼之间的临时接触进行建模。为了解决这些问题，我们提出了交互式双流图神经网络，它采用关节-骨骼通信块来加速关节流和骨骼流之间的交互。此外，引入了自适应策略以实现顶点之间的动态连接。在三个大规模数据集上的大量实验证明了我们提出的方法的有效性。