Skip to main content
Fig. 2 | Journal of NeuroEngineering and Rehabilitation

Fig. 2

From: Automated freezing of gait assessment with marker-based motion capture and multi-stage spatial-temporal graph convolutional neural networks

Fig. 2

Overview of the multi-stage graph convolutional neural network architecture (MS-GCN). MS-GCN generates an initial prediction with multiple blocks of spatial-temporal graph convolutional neural network (ST-GCN) layers and refines the predictions over several stages with multiple blocks of temporal convolutional (TCN) layers. An ST-GCN block is visualized in blue and a TCN block in gray

Back to article page