Abstract: Graph Convolution Networks (GCNs) have achieved remarkable success in representation of structured graph data. As we know that traditional GCNs are generally defined on the fixed first-order ...
Abstract: In this paper, we present a novel convolution theorem which encompasses the well known convolution theorem in (graph) signal processing as well as the one related to time-varying filters.
Semantic-STGCNN is a novel deep learning framework for human trajectory prediction that integrates semantic environmental information with spatio-temporal graph convolutional neural networks. This ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback