The ability to predict, anticipate and reason about future outcomes is a key component of
intelligent decision-making systems. In light of the success of deep learning in computer …

Abstract From CNN, RNN, to ViT, we have witnessed remarkable advancements in video
prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated …

The predictive learning of spatiotemporal sequences aims to generate future images by
learning from the historical context, where the visual dynamics are believed to have modular …

Spatiotemporal prediction is challenging due to the complex dynamic motion and
appearance changes. Existing work concentrates on embedding additional cells into the …

Pedestrian behavior anticipation is a key challenge in the design of assistive and
autonomous driving systems suitable for urban environments. An intelligent system should …

This paper offers an insightful examination of how currently top-trending AI technologies, ie,
generative artificial intelligence (Generative AI) and large language models (LLMs), are …

Collaborative perception has recently shown great potential to improve perception
capabilities over single-agent perception. Existing collaborative perception methods usually …

Leveraging physical knowledge described by partial differential equations (PDEs) is an
appealing way to improve unsupervised video forecasting models. Since physics is too …

Spatiotemporal predictive learning, though long considered to be a promising self-
supervised feature learning method, seldom shows its effectiveness beyond future video …

Natural spatiotemporal processes can be highly non-stationary in many ways, eg the low-
level non-stationarity such as spatial correlations or temporal dependencies of local pixel …