Generative Adversarial Networks for Spatio-temporal Data: A Survey

Generative Adversarial Networks (GANs) have shown remarkable success in producing realistic-looking images the computer vision area. Recently, GAN-based techniques are to be promising for spatio-temporal-based applications such as trajectory prediction, events generation, and time-series data imputation. While several reviews GANs been presented, no one has considered addressing practical challenges relevant spatio-temporal data. In this article, we conducted a comprehensive review of recent developments We summarise application popular GAN architectures common practices evaluating performance with GANs. Finally, point out future research directions benefit researchers