tsl: a PyTorch library for processing spatiotemporal data.

"Graph Neural Controlled Differential Equations for Traffic Forecasting", AAAI 2022

Code for: "Skeleton-Graph: Long-Term 3D Motion Prediction From 2D Observations Using Deep Spatio-Temporal Graph CNNs", ICCV2021 Workshops

S&P100 stocks analysis via Graph Neural Networks (Forecasting, Clustering, Trend classification, Stocks ranking for optimal stock picking)

An eXplainable AI system to elucidate short-term speed forecasts in traffic networks obtained by Spatio-Temporal Graph Neural Networks.

This repository contains de code and instructions to train the models and prepare the datasets for the experiments in the paper "Atom: Neural Traffic Compression with Spatio-Temporal Graph Neural Networks" accepted at the 2nd ACM CONEXT GNNet 2023 Workshop.

Video Query System