mlsanityData to 14 Oct 2026

FootBots: A Transformer-based Architecture for Motion Prediction in Soccer

arXiv 2406.19852 ↗First posted 28 Jun 2024cs.CV cs.MAcited by 8

Not on the map. Why?

Abstract (arXiv)

Motion prediction in soccer involves capturing complex dynamics from player and ball interactions. We present FootBots, an encoder-decoder transformer-based architecture addressing motion prediction and conditioned motion prediction through equivariance properties. FootBots captures temporal and social dynamics using set attention blocks and multi-attention block decoder. Our evaluation utilizes two datasets: a real soccer dataset and a tailored synthetic one. Insights from the synthetic dataset highlight the effectiveness of FootBots' social attention mechanism and the significance of conditioned motion prediction. Empirical results on real soccer data demonstrate that FootBots outperforms baselines in motion prediction and excels in conditioned tasks, such as predicting the players based on the ball position, predicting the offensive (defensive) team based on the ball and the defensive (offensive) team, and predicting the ball position based on all players. Our evaluation connects quantitative and qualitative findings. https://youtu.be/9kaEkfzG3L8

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 28 Jun 2024.

Builds on

18 of 27 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 690
  3. 2017On human motion prediction using recurrent neural networkscited by 338
  4. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 331
  5. 2019Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019cited by 273
  6. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 229
  7. 2020A Spatio-temporal Transformer for 3D Human Motion Predictioncited by 133
  8. 2021Latent Variable Sequential Set Transformers For Joint Multi-Agent Motion Predictioncited by 131
  9. 2022Back to MLP: A Simple Baseline for Human Motion Predictioncited by 100
  10. 2017Coordinated Multi-Agent Imitation Learningcited by 72
  11. 2018Generating Multi-Agent Trajectories using Programmatic Weak Supervisioncited by 46
  12. 2019Stochastic Prediction of Multi-Agent Interactions from Partial Observationscited by 26
6 more
  1. 2017Generating Long-term Trajectories Using Deep Hierarchical Networkscited by 23
  2. 2022Evaluation of creating scoring opportunities for teammates in soccer via trajectory predictioncited by 20
  3. 2020Multi-Modal Trajectory Prediction of NBA Playerscited by 19
  4. 2021baller2vec: A Multi-Entity Transformer For Multi-Agent Spatiotemporal Modelingcited by 14
  5. 2021baller2vec++: A Look-Ahead Multi-Entity Transformer For Modeling Coordinated Agentscited by 12
  6. 2020A Graph Attention Based Approach for Trajectory Prediction in Multi-agent Sports Gamescited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2025Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modelingcited by 15
  2. 2024TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sportscited by 11
  3. 2025FOOTPASS: A Multi-Modal Multi-Agent Tactical Context Dataset for Play-by-Play Action Spotting in Soccer Broadcast Videoscited by 5
  4. 2026Heteroscedastic Diffusion for Multi-Agent Trajectory Modelingcited by 3
  5. 2025Multi-Modal Soccer Scene Analysis with Masked Pre-Trainingcited by 1
  6. 2026Decoding Defensive Coverage Responsibilities in American Football Using Factorized Attention Based Transformer Modelscited by 1
  7. 2025CourtMotion: Learning Event-Driven Motion Representations from Skeletal Data for Basketballcited by 0
  8. 2026Synthetic-to-Real Translation for Class-Agnostic Motion Predictioncited by 0