Abstract
Traffic is a highly dynamic system containing spatial, temporal and random patterns. Spatial Temporal Graph Neural Networks(STGNNs) model traffic as an evolving graph, dynamically capturing both spatial and temporal patterns. Current evaluation metrics (mean errors) do not show model performance in real world scenarios. We train and evaulate baseline and State of the art STGNNs as well as develop a visualization framework to evaluate these models in real world scenarios.
Videos 1
Watch presentations, demos, and related content
Like, comment, and subscribe on YouTube to support the creator!
Gallery 1
Explore the visual story of this exhibit
Title Image