Human activity recognition (HAR) is one of the most important and challenging problems in
the computer vision. It has critical application in wide variety of tasks including gaming …

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 …

Conventionally, Earth system (eg, weather and climate) forecasting relies on numerical
simulation with complex physical models and hence is both expensive in computation and …

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 …

In humans, Attention is a core property of all perceptual and cognitive operations. Given our
limited ability to process competing sources, attention mechanisms select, modulate, and …

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

Accurate traffic flow prediction is valuable for satisfying citizens' travel needs and alleviating
urban traffic pressure. However, it is highly challenging due to the complexity of the urban …

Spatiotemporal predictive learning aims to generate future frames by learning from historical
frames. In this paper, we investigate existing methods and present a general framework of …

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