Intention Driven Identification of In-Possession Match Phases in Association Football through Temporal Graph Learning

📄 arXiv: 2606.09289v1 📥 PDF

作者: Yuesen Li, Daniel Link

分类: cs.LG

发布日期: 2026-06-08

备注: 27 pages, 10 figures


💡 一句话要点

提出基于时序图学习的框架以识别足球比赛中的持球阶段

🎯 匹配领域: 支柱八:物理动画 (Physics-based Animation)

关键词: 足球战术分析 时序图学习 持球阶段识别 图神经网络 自动比赛注释 数据驱动方法

📋 核心要点

  1. 现有方法难以直接观察持球阶段,且缺乏对战术意图的深入理解,导致阶段识别的准确性不足。
  2. 本文提出了一种基于时序图注意力网络的框架,结合了球员交互图和上下文特征,以识别持球阶段。
  3. 实验结果表明,T-GAN在意图层面和阶段层面的F1分数分别达到了0.87和0.79,显著提高了识别的时序一致性。

📝 摘要(中文)

理解足球的战术组织需要识别不同的比赛阶段。然而,持球阶段往往难以直接观察,且受到不断变化的战术意图影响,而不仅仅是空间模式。本文提出了一种数据驱动的框架,通过时空跟踪数据识别持球阶段。分析了七场德国足球甲级联赛的比赛,定义了一个包含三种战术意图和六个阶段的分层阶段模型。开发了时序图注意力网络(T-GAN),结合了帧级球员交互图、上下文特征和基于Transformer的时序建模。评估结果显示,T-GAN在意图层面和阶段层面的F1分数均有显著提升,表明该框架在自动比赛注释、战术分析和风格分析等方面具有潜在应用价值。

🔬 方法详解

问题定义:本文旨在解决如何从时空跟踪数据中识别足球比赛中的持球阶段。现有方法往往忽视了战术意图的动态变化,导致阶段识别的准确性不足。

核心思路:提出了一种数据驱动的框架,利用时序图注意力网络(T-GAN)来结合球员交互图和上下文特征,从而更好地捕捉持球阶段的战术意图。

技术框架:整体架构包括数据预处理、时序图构建、特征提取和模型训练四个主要模块。通过将帧级数据转化为图结构,模型能够有效捕捉球员之间的关系和动态变化。

关键创新:最重要的技术创新在于引入了时序图注意力机制,使得模型能够在时序数据中有效识别和区分不同的战术意图和比赛阶段,这与传统的基于空间模式的方法有本质区别。

关键设计:模型采用了多层图卷积网络和Transformer结构,损失函数设计为结合帧级F1和IoT-D指标,以优化模型在不同层面的表现。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,T-GAN在意图层面的宏平均F1分数达到0.87,阶段层面的F1分数为0.79,经过后处理后,意图的IoT-D F1从0.68提升至0.79,阶段的IoT-D F1从0.61提升至0.71,表明模型在时序一致性方面有显著改善。

🎯 应用场景

该研究的潜在应用领域包括自动比赛注释、战术分析和球队风格分析。通过将连续的跟踪数据转化为可解释的战术阶段表示,教练和分析师可以更好地理解比赛动态,从而制定更有效的战术策略。

📄 摘要(原文)

Understanding tactical organisation of association football, hereafter referred to as football, requires identifying distinct match phases. Yet in-possession phases are rarely directly observable and are shaped by evolving tactical intentions, rather than spatial patterns alone. This study proposes a data-driven framework for identifying in-possession match phases from spatiotemporal tracking data. Seven German Bundesliga matches recorded at 25 Hz with TRACAB were analysed. A hierarchical phase model was defined with three tactical intentions (Invade Opponent Space, Keep Possession, Scoring) and six phases (Build Up, Progression, Counter Attack, Maintenance, Sustained Threat, Finishing). A Temporal Graph Attention Network (T-GAN) was developed to combine frame-level player-interaction graphs, contextual features, and Transformer-based temporal modelling. Performance was evaluated using frame-level F1 and a sequence-aware Intersection over Truth-Dominance (IoT-D) metric. T-GAN achieved macro-average frame-level F1 scores of 0.87 at the intention level, 0.76 for invasion-related phases, and 0.79 for scoring phases. At the sequence level, mean diagonal IoT-D F1 increased from 0.68 to 0.79 for intentions and from 0.61 to 0.71 for phases after post-processing, indicating improved temporal coherence. Model comparisons showed that sequence modelling was the main driver of segmentation quality, while graph-based relational modelling was particularly beneficial for Counter Attack recognition. Exploratory player attention analysis further suggested that wide and midfield positional groups contributed strongly to phase discrimination. Overall, the framework translates continuous tracking data into tactically interpretable in-possession phase representations, with potential applications in automated match annotation, tactical analysis, and playing-style profiling.