Tingwei Li, Ruiwen Zhang, Qing Li, Tsinghua University, China

Graph convolutional networks (GCNs) can effectively capture the features of related nodes and improve the performance of model. More attention is paid to employing GCN in Skeleton-Based action recognition. But existing methods based on GCNs have two problems. First, the consistency of temporal and spatial features is ignored for extracting features node by node and frame by frame. To obtain spatiotemporal features simultaneously, we design a generic representation of skeleton sequences for action recognition and propose a novel model called Temporal Graph Networks (TGN). Secondly, the adjacency matrix of graph describing the relation of joints are mostly depended on the physical connection between joints. To appropriate describe the relations between joints in skeleton graph, we propose a multi-scale graph strategy, adopting a full-scale graph, part-scale graph and core-scale graph to capture the local features of each joint and the contour features of important joints. Experiments were carried out on two large datasets and results show that TGN with our graph strategy outperforms state-of-the-art methods.

Skeleton-based action recognition, Graph convolutional network, Multi-scale graphs.