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 …

In a world with rapidly growing levels of automation, robotics is playing an increasingly
significant role in every aspect of human endeavour. In particular, many types of mobile …

Video prediction is a challenging task. The quality of video frames from current state-of-the-
art (SOTA) generative models tends to be poor and generalization beyond the training data …

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

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

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

We present PredRNN++, a recurrent network for spatiotemporal predictive learning. In
pursuit of a great modeling capability for short-term video dynamics, we make our network …

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

Being able to predict what may happen in the future requires an in-depth understanding of
the physical and causal rules that govern the world. A model that is able to do so has a …

A video prediction model that generalizes to diverse scenes would enable intelligent agents
such as robots to perform a variety of tasks via planning with the model. However, while …