# Inferring Player Location in Sports Matches: Multi-Agent Spatial Imputation from Limited Observations

arXiv: https://arxiv.org/abs/2302.06569 · HTML: https://mlsanity.com/paper/2302.06569/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 32 references that are in the map.
- First posted on arXiv 13 Feb 2023.

## Builds on (most cited first, 8 of 8)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Coordinated Multi-Agent Imitation Learning](https://mlsanity.com/paper/1703.03121/) (2017)
- [Stochastic Prediction of Multi-Agent Interactions from Partial Observations](https://mlsanity.com/paper/1902.09641/) (2019)
- [Congestion-aware Multi-agent Trajectory Prediction for Collision Avoidance](https://mlsanity.com/paper/2103.14231/) (2021)
- [Multi-Modal Trajectory Prediction of NBA Players](https://mlsanity.com/paper/2008.07870/) (2020)
- [SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction](https://mlsanity.com/paper/2007.13078/) (2020)
- [Optimising Game Tactics for Football](https://mlsanity.com/paper/2003.10294/) (2020)
- [Optimising Long-Term Outcomes using Real-World Fluent Objectives: An Application to Football](https://mlsanity.com/paper/2102.09469/) (2021)

## Built on by (most cited first, 9 of 9)

- [TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports](https://mlsanity.com/paper/2410.17785/) (2024)
- [Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networks](https://mlsanity.com/paper/2502.15462/) (2025)
- [Continuous football player tracking from discrete broadcast data](https://mlsanity.com/paper/2311.14642/) (2023)
- [Multi-Modal Soccer Scene Analysis with Masked Pre-Training](https://mlsanity.com/paper/2512.19528/) (2025)
- [Training-Free Off-Screen Player Imputation for Broadcast-Based Spatial Football Analytics](https://mlsanity.com/paper/2607.11548/) (2026)
- [Space-Creating versus Dead Possession: An Off-Ball Possession-Quality Index for Broadcast Football](https://mlsanity.com/paper/2608.09887/) (2026)
- [The Strain of Success: A Predictive Model for Injury Risk Mitigation and Team Success in Soccer](https://mlsanity.com/paper/2402.04898/) (2024)
- [PathCRF: Ball-Free Soccer Event Detection via Possession Path Inference from Player Trajectories](https://mlsanity.com/paper/2602.12080/) (2026)
- [How Much Velocity Does Off-Ball Space Value Need? A Broadcast-Viewport Benchmark](https://mlsanity.com/paper/2609.10801/) (2026)

## Abstract (arXiv)

Understanding agent behaviour in Multi-Agent Systems (MAS) is an important problem in domains such as autonomous driving, disaster response, and sports analytics. Existing MAS problems typically use uniform timesteps with observations for all agents. In this work, we analyse the problem of agent location imputation, specifically posed in environments with non-uniform timesteps and limited agent observability (~95% missing values). Our approach uses Long Short-Term Memory and Graph Neural Network components to learn temporal and inter-agent patterns to predict the location of all agents at every timestep. We apply this to the domain of football (soccer) by imputing the location of all players in a game from sparse event data (e.g., shots and passes). Our model estimates player locations to within ~6.9m; a ~62% reduction in error from the best performing baseline. This approach facilitates downstream analysis tasks such as player physical metrics, player coverage, and team pitch control. Existing solutions to these tasks often require optical tracking data, which is expensive to obtain and only available to elite clubs. By imputing player locations from easy to obtain event data, we increase the accessibility of downstream tasks.