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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces a multi-resolution spatial partitioning and scan statistic method to detect unfairness in predictive models based on movement patterns, validated as effective on synthetic datasets.
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.
-
Assessing Predictive Models for Fairness Based on Movement Patterns
Introduces a multi-resolution spatial partitioning and scan statistic method to detect unfairness in predictive models based on movement patterns, validated as effective on synthetic datasets.