This review paper provides an overview of deep learning approaches for trajectory data. The authors identify eight specific mobility use cases, analyzing the deep learning models and training data used. The paper also provides a data-centric analysis of recent work in this field, placing it along the mobility data continuum which ranges from detailed dense trajectories of individual movers to sparse trajectories (such as check-in data), and aggregated trajectories (crowd information). The review underlines the importance of understanding the type of trajectory data used to train deep learning models.
Publication date: 1 Feb 2024
Project Page: https://arxiv.org/abs/2402.00732
Paper: https://arxiv.org/pdf/2402.00732
