Learning Spatio-Temporal Behavioural Representations for Urban Activity Forecasting

The vagueness of the concept of resilience makes it difficult to define unanimously, and it becomes even more problematic when it comes to measuring it, while urban resilience metrics can be considered as key indicators transmitting vital ...

In the wake of many new ML-inspired approaches for reconstructing and representing high-quality 3D content, recent hybrid and explicitly learned representations exhibit promising performance and quality characteristics. However, their scaling to higher ...

Urban hotspot forecasting is one of the most important tasks for resource scheduling and security in future smart cities. Most previous works employed fixed neural architectures based on many complicated spatial and temporal learning modules. ...

• Forecasting urban hotspot with automated spatio-temporal information fusion network.
• Introducing multi-scale spatio-temporal operations for neural architectures search.
• Searching more effective spatio-temporal information fusion ...