T-GAN segments football matches into intention-driven in-possession phases using player interaction graphs and transformers on 25 Hz tracking data from seven Bundesliga matches, achieving frame-level F1 of 0.87 for intentions.
Frontiers in Sports and Active Living7(2025) https://doi.or g/10.3389/fspor.2025.1569155
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Expected Threat model error follows an approximate log-normal distribution, enabling rules of thumb for reliable use in football player evaluation despite unobservable ground truth.
citing papers explorer
-
Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning
T-GAN segments football matches into intention-driven in-possession phases using player interaction graphs and transformers on 25 Hz tracking data from seven Bundesliga matches, achieving frame-level F1 of 0.87 for intentions.
-
Model quality in football: Quantifying the quality of an Expected Threat model
Expected Threat model error follows an approximate log-normal distribution, enabling rules of thumb for reliable use in football player evaluation despite unobservable ground truth.