Spatio-temporal aggregation of skeletal motion features for human motion prediction

Abstract

This study proposes a human body motion prediction model that can adapt to the disorders in various human motion patterns and represent the kinematic constraints. In human motion prediction, the acquisition of features that capture inter-motion and inter-joint linkages is considered effective. To generate links that are adaptive to the reference time of dominant features and their crossing-over joints, we construct an attention-based network that aggregates motion sequences temporally and spatially. We evaluated the motion prediction results using the Human3.6M dataset with the indices of mean angle error and mean per joint position error and showed that our method outperforms other state-of-the-art methods.