Graph convolutional networks (GCNs) based methods have achieved advanced performance on skeleton-based action recognition task. However, the skeleton graph cannot fully represent the motion information contained in skeleton data. In addition, the topology of the skeleton graph in the GCN-based methods is manually set according to natural connections, and it is fixed for all samples, which cannot well adapt to different situations. In this work, we propose a novel dynamic hypergraph convolutional networks (DHGCN) for skeleton-based action recognition. DHGCN uses hypergraph to represent the skeleton structure to effectively exploit the motion information contained in human joints. Each joint in the skeleton hypergraph is dynamically assigned the corresponding weight according to its moving, and the hypergraph topology in our model can be dynamically adjusted to different samples according to the relationship between the joints. Experimental results demonstrate that the performance of our model achieves competitive performance on three datasets: Kinetics-Skeleton 400, NTU RGB+D 60, and NTU RGB+D 120.
翻译:在基于骨骼的动作识别任务上,基于图形的变动网络(GCN)方法已经取得了先进的表现。然而,骨架图无法充分反映骨架数据中包含的运动信息。此外,基于GCN方法中的骨架图的表层根据自然连接量手工设定,为所有样本固定,这些样本无法很好地适应不同的情况。在这项工作中,我们提出了一个新的基于骨架的动作识别动态高传网络(DHGCN)。DHGCN使用高光谱来代表骨架结构,以有效地利用人类关节中包含的运动信息。骨架高光图中的每一个联合都根据运动动态地分配相应的重量,而我们模型中的高光谱表层可以动态地根据联合之间的关系根据不同的样本进行调整。实验结果表明,我们模型的性能在三个数据集上取得了竞争性的性能:Kinitics-Skeleton 400、NTU RGB+D 60和NTU RGB+D 120,以及NTU RGB+D 120。实验结果表明,我们模型的性能在三个数据集上取得竞争性的性表现:Keticts-Skeet-Sketon 400、Skeleton-Skele-D-D-60和NTUD+D 120。