Learning Priors of Human Motion With Vision Transformers

A clear understanding of where humans move in a scenario, their usual paths and speeds, and where they stop, is very important for different applications, such as mobility studies in urban areas or robot navigation tasks within humanpopulated environments. We propose in this article, a neural architecture based on Vision Transformers (ViTs) to provide this information. This solution can arguably capture spatial correlations more effectively than Convolutional Neural Networks (CNNs). In the paper, we describe the methodology and proposed neural architecture and show the experiments’ results with a standard dataset. We show that the proposed ViT architecture improves the metrics compared to a method based on a CNN. Index Terms—vision transformers, human motion prediction, semantic scene understanding, masked autoencoders, occupancy priors.