Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting

Luca Hermes, Barbara Hammer, Malte Schilling
2021 ESANN 2021 proceedings   unpublished
Prediction of movements is essential for successful cooperation with intelligent systems. We propose a model that integrates organized spatial information as given through the moving body's skeletal structure. This inherent structure is exploited in our model through application of Graph Convolutions and we demonstrate how this allows leveraging the structured spatial information into competitive predictions that are based on a lightweight model that requires a comparatively small number of
more » ... meters. In this section, we describe the experiments we conducted on the presented model. To quantify the performance, we perform an evaluation using protocols
doi:10.14428/esann/2021.es2021-145 fatcat:fj4p5e5rbnctljezan6rcqz7lu