View-adaptive graph neural network for action recognition

Abstract

Skeleton-based recognition of human actions has received attention in recent years because of the popularity of 3-D acquisition sensors. Existing studies use 3-D skeleton data from video clips collected from several views. The body view shifts from the camera perspective when humans perform certain actions, resulting in unstable and noisy skeletal data. In this article, we developed a view-adaptive (VA) mechanism that identifies the viewpoints across the sequence and transforms the skeleton view through a data-driven learning process to counteract the influence of variations. Most existing methods use fixed human-defined prior criterion to reposition skeletons. We utilized an unsupervised reposition approach and jointly designed a VA neural network based on the graph neural network (GNN). Our VA-GNN model can transform the skeletons of distinct views into a considerably more consistent virtual perspective over preprocessing approach. The VA module learns the best observed view because it determines the most suitable view and transforms the skeletons from the action sequence for end-to-end recognition along with suited graph topology with adaptive GNN. Thus, our strategy reduces the influence of view variance, allowing networks to focus on learning action-specific properties and resulting in improved performance. The accuracy achieved by the experiments on the four benchmark data sets.