Interactive sequential generative models for team sports

Research output: Journal contributionsJournal articlesResearchpeer-review

Standard

Interactive sequential generative models for team sports. / Fassmeyer, Dennis; Cordes, Moritz; Brefeld, Ulf.
In: Machine Learning, Vol. 114, No. 2, 38, 02.2025.

Research output: Journal contributionsJournal articlesResearchpeer-review

Harvard

APA

Vancouver

Fassmeyer D, Cordes M, Brefeld U. Interactive sequential generative models for team sports. Machine Learning. 2025 Feb;114(2):38. doi: 10.1007/s10994-024-06648-2

Bibtex

@article{4cc4188e57574979abe1c5f5796a3e6f,
title = "Interactive sequential generative models for team sports",
abstract = "Understanding spatiotemporal coordination of players in team sports is key to movement models, pattern detection, and computational tactics. Existing generative models propose to capture all stochasticity by a single latent variable and may suffer from entangled representations, or aim to uncover interaction structures of players but then do not focus on their generative ability. As a remedy, we propose a hierarchical latent variable model for predicting trajectories of multiple players. In the generative model, both, discrete role assignments and a latent interaction graph are sampled to allow for different models in subsequent node updates and message passing operations between nodes, where standard Gaussian latent variables are employed per agent and timestep. We cast our approach as a variational autoencoder that provides a disentangled latent space to capture variability in team sport movements and propose a neural architecture for its optimization. We empirically evaluate our approach on tracking data from basketball and soccer and observe that our contribution outperforms the state-of-art in all experiments.",
keywords = "Generative models, Graph recurrent neural networks, Soccer, Socio-temporal dependencies, Trajectory forecasting, Informatics",
author = "Dennis Fassmeyer and Moritz Cordes and Ulf Brefeld",
note = "Publisher Copyright: {\textcopyright} The Author(s) 2025.",
year = "2025",
month = feb,
doi = "10.1007/s10994-024-06648-2",
language = "English",
volume = "114",
journal = "Machine Learning",
issn = "0885-6125",
publisher = "Springer Netherlands",
number = "2",

}

RIS

TY - JOUR

T1 - Interactive sequential generative models for team sports

AU - Fassmeyer, Dennis

AU - Cordes, Moritz

AU - Brefeld, Ulf

N1 - Publisher Copyright: © The Author(s) 2025.

PY - 2025/2

Y1 - 2025/2

N2 - Understanding spatiotemporal coordination of players in team sports is key to movement models, pattern detection, and computational tactics. Existing generative models propose to capture all stochasticity by a single latent variable and may suffer from entangled representations, or aim to uncover interaction structures of players but then do not focus on their generative ability. As a remedy, we propose a hierarchical latent variable model for predicting trajectories of multiple players. In the generative model, both, discrete role assignments and a latent interaction graph are sampled to allow for different models in subsequent node updates and message passing operations between nodes, where standard Gaussian latent variables are employed per agent and timestep. We cast our approach as a variational autoencoder that provides a disentangled latent space to capture variability in team sport movements and propose a neural architecture for its optimization. We empirically evaluate our approach on tracking data from basketball and soccer and observe that our contribution outperforms the state-of-art in all experiments.

AB - Understanding spatiotemporal coordination of players in team sports is key to movement models, pattern detection, and computational tactics. Existing generative models propose to capture all stochasticity by a single latent variable and may suffer from entangled representations, or aim to uncover interaction structures of players but then do not focus on their generative ability. As a remedy, we propose a hierarchical latent variable model for predicting trajectories of multiple players. In the generative model, both, discrete role assignments and a latent interaction graph are sampled to allow for different models in subsequent node updates and message passing operations between nodes, where standard Gaussian latent variables are employed per agent and timestep. We cast our approach as a variational autoencoder that provides a disentangled latent space to capture variability in team sport movements and propose a neural architecture for its optimization. We empirically evaluate our approach on tracking data from basketball and soccer and observe that our contribution outperforms the state-of-art in all experiments.

KW - Generative models

KW - Graph recurrent neural networks

KW - Soccer

KW - Socio-temporal dependencies

KW - Trajectory forecasting

KW - Informatics

UR - http://www.scopus.com/inward/record.url?scp=85217779916&partnerID=8YFLogxK

U2 - 10.1007/s10994-024-06648-2

DO - 10.1007/s10994-024-06648-2

M3 - Journal articles

VL - 114

JO - Machine Learning

JF - Machine Learning

SN - 0885-6125

IS - 2

M1 - 38

ER -

Recently viewed

Publications

  1. Light availability and land-use history drive biodiversity and functional changes in forest herb layer communities
  2. Comparison of EKF and TSO for Health Monitoring of a Textile-Based Heater Structure and its Control
  3. CETUS – a baseline approach to type extraction
  4. How to Do Materialistic Dialectics with Words?
  5. Foreign bias in institutional portfolio allocation
  6. How can problems be turned into something good? The role of entrepreneurial learning and error mastery orientation
  7. Transformation products in the water cycle and the unsolved problem of their proactive assessment
  8. The case of the composite Higgs
  9. Integration of laboratory experiments into introductory electrical engineering courses
  10. Conceptualizing community in energy systems
  11. Circular Scanning Resolution Improvement by its Velocity Close Loop Control
  12. Understanding and managing post-acquisition integration as change process
  13. Priority Rule-based Planning Approaches for Regeneration Processes
  14. Abjection and Formlessness
  15. Facilitating collaborative processes in transdisciplinary research using design prototyping
  16. A Multilab Replication of the Ego Depletion Effect
  17. Authority and Authorship
  18. Introduction
  19. Identification and Root Cause Mapping of Supply Chain Collaboration Resistors
  20. Self-perceived quality of life predicts mortality risk better than a multi-biomarker panel, but the combination of both does best
  21. Generalized self-efficacy as a mediator and moderator between control and complexity at work and personal initiative
  22. Complexity and Administrative Intensity
  23. Indicator model of students' writing skills (IMOSS)
  24. Shared mobility business models
  25. How cognitive issue bracketing affects interdependent decision-making in negotiations
  26. Subsistence and substitutability in consumer preferences
  27. Anonymized Firm Data under Test: Evidence from a Replication Study
  28. Learning to collaborate from diverse interactions in project-based sustainability courses
  29. Project-Mentoring in Engineering Education - a competence-oriented teaching and learning approach
  30. Digital identity building:
  31. An Off-the-shelf Approach to Authorship Attribution