Game State and Spatio-Temporal Action Detection in Soccer Using Graph Neural Networks and 3D Convolutional Networks

Jérémie Ochin, Jérémie Ochin, Guillaume Devineau, Bogdan Stanciulescu, Sotiris Manitsaris

2025

Abstract

Soccer analytics rely on two data sources: the player positions on the pitch and the sequences of events they perform. With around 2000 ball events per game, their precise and exhaustive annotation based on a monocular video stream remains a tedious and costly manual task. While state-of-the-art spatio-temporal action detection methods show promise for automating this task, they lack contextual understanding of the game. Assuming professional players’ behaviors are interdependent, we hypothesize that incorporating surrounding players’ information such as positions, velocity and team membership can enhance purely visual predictions. We propose a spatio-temporal action detection approach that combines visual and game state information via Graph Neural Networks trained end-to-end with state-of-the-art 3D CNNs, demonstrating improved metrics through game state integration.

Paper Citation

in Harvard Style

Ochin J., Devineau G., Stanciulescu B. and Manitsaris S. (2025). Game State and Spatio-Temporal Action Detection in Soccer Using Graph Neural Networks and 3D Convolutional Networks. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 636-646. DOI: 10.5220/0013161100003905

in Bibtex Style

@conference{icpram25,
author={Jérémie Ochin and Guillaume Devineau and Bogdan Stanciulescu and Sotiris Manitsaris},
title={Game State and Spatio-Temporal Action Detection in Soccer Using Graph Neural Networks and 3D Convolutional Networks},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={636-646},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013161100003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Game State and Spatio-Temporal Action Detection in Soccer Using Graph Neural Networks and 3D Convolutional Networks
SN - 978-989-758-730-6
AU - Ochin J.
AU - Devineau G.
AU - Stanciulescu B.
AU - Manitsaris S.
PY - 2025
SP - 636
EP - 646
DO - 10.5220/0013161100003905
PB - SciTePress