Fast 3D-graph convolutional networks for skeleton-based action recognition

Research on human action recognition based on skeletons has received much attention. But most of the research focuses on improving the model's generalization ability, while ignoring significant efficiency issues. This leads to developing heavy models with poor scalability and cost-effectiveness in practical use. This paper, we investigate the under-studied but practically critical recognition model efficiency problem. To this end, we present a new Fast Recognition Distillation (FRD) model learning strategy. Specifically, FRD trains a lightweight recognition neural network structure that can be quickly executed at a low computational cost. It can be achieved by effectively disseminating the identification probability information of the teacher network to the lightweight network. We call the probability information of the teacher network as soft-target, and FRD can learn more potential information from soft-target. In addition, we also used a particular loss function for soft-target. Through the FRD network, while basically maintaining the recognition accuracy, we minimized the network structure. Extensive experiments on the two large-scale datasets, NTU-RGBD and Kinetics-Skeleton, demonstrate that our model (FRD) is more lightweight and refined than others. Therefore, our model FRD is efficient. (c) 2023 Elsevier B.V. All rights reserved.