![[2602.18519] Wide Open Gazes: Quantifying Visual Exploratory Behavior in Soccer with Pose Enhanced Positional Data](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.18519] Wide Open Gazes: Quantifying Visual Exploratory Behavior in Soccer with Pose Enhanced Positional Data
Summary
This paper presents a novel approach to quantifying visual exploratory behavior in soccer using pose-enhanced positional data, addressing limitations of traditional methods.
Why It Matters
Understanding visual exploratory behavior in soccer can enhance player performance analysis and strategy development. This research introduces a continuous measurement method that integrates seamlessly with existing analytics frameworks, making it a significant advancement in sports analytics.
Key Takeaways
- Introduces a continuous stochastic vision layer for visual behavior analysis.
- Eliminates player position bias and manual annotation requirements.
- Demonstrates predictive metrics for on-ball performance using real game data.
- Integrates with existing soccer analytics frameworks for broader applicability.
- Open-sources tools for implementing the proposed methodology.
Computer Science > Machine Learning arXiv:2602.18519 (cs) [Submitted on 19 Feb 2026] Title:Wide Open Gazes: Quantifying Visual Exploratory Behavior in Soccer with Pose Enhanced Positional Data Authors:Joris Bekkers View a PDF of the paper titled Wide Open Gazes: Quantifying Visual Exploratory Behavior in Soccer with Pose Enhanced Positional Data, by Joris Bekkers View PDF Abstract:Traditional approaches to measuring visual exploratory behavior in soccer rely on counting visual exploratory actions (VEAs) based on rapid head movements exceeding 125°/s, but this method suffer from player position bias (i.e., a focus on central midfielders), annotation challenges, binary measurement constraints (i.e., a player is scanning, or not), lack the power to predict relevant short-term in-game future success, and are incompatible with fundamental soccer analytics models such as pitch control. This research introduces a novel formulaic continuous stochastic vision layer to quantify players' visual perception from pose-enhanced spatiotemporal tracking. Our probabilistic field-of-view and occlusion models incorporate head and shoulder rotation angles to create speed-dependent vision maps for individual players in a two-dimensional top-down plane. We combine these vision maps with pitch control and pitch value surfaces to analyze the awaiting phase (when a player is awaiting the ball to arrive after a pass for a teammate) and their subsequent on-ball phase. We demonstrate that aggregated v...