The paper introduces Graph-to-Grid (G2G), a method that paints continuous‑coordinate player features onto a grid using bilinear interpolation, enabling end‑to‑end training of per‑player encoders for pass surface prediction. On 53,628 World Cup passes, this painting approach improves selection likelihood by about a quarter of a nat compared to raster‑only inputs, with further gains from learned encoders and message passing. The study also shows that painting benefits existing models like SoccerMap and U‑Net, while other variants such as offset channels or raster‑free decoders do not provide similar improvements.
arXiv:2607. 11548v1 Announce Type: cross Abstract: Spatial football metrics such as pitch control assume access to the positions of all 22 players, yet the most widely available source of positional data -- the broadcast main camera -- shows only 10-16 of them at any moment.
arXiv:2607. 14616v1 Announce Type: new Abstract: Vision--language models have become increasingly capable of interpreting visual scenes, but it remains unclear whether they can use information to make strategically effective decisions.
arXiv:2609.25569v1 Announce Type: new Abstract: Soccer tactics are interactive: an attacking action changes the opponent's defensive problem, and the observed response depends on the multi-agent matc...
Soccer tactics are interactive: an attacking action changes the opponent's defensive problem, and the observed response depends on the multi-agent match state. We introduce SambaGraph, an action--reac...
arXiv:2602. 12080v2 Announce Type: replace Abstract: Despite recent advances in AI, event data collection in soccer still relies heavily on labor-intensive manual annotation.
The paper introduces the Hierarchical Possession-aware Graph Pointer Network (HPGPN) for selecting pass receivers in football analytics. HPGPN treats the task as a variable-size candidate prediction problem, modeling current player interactions, local event context, and possession-level temporal dynamics using a graph representation. Experiments on public football event and freeze-frame datasets show that HPGPN improves pass receiver selection performance, with ablation studies confirming the value of graph-based interaction modeling, fixed event context, and dual-branch dynamic possession-history modeling.
Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough for deployment. Ama...
arXiv:2608. 09887v1 Announce Type: cross Abstract: Ball possession is the most-cited and most-misleading number in football: 60% recycled in one's own half is not 60% spent pinning the opponent back.
arXiv:2607. 17765v1 Announce Type: cross Abstract: We introduce WC2026-Agents, a benchmark and dataset for evaluating large language models (LLMs) as autonomous forecasting agents on real, future events.
arXiv:2606. 09289v1 Announce Type: new Abstract: Understanding tactical organisation of association football, hereafter referred to as football, requires identifying distinct match phases.
arXiv:2609.28049v1 Announce Type: cross Abstract: Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as ev...
Location encoders transform geographic coordinates into high‑dimensional embeddings for machine learning, yet it is unclear how well these embeddings capture interpretable spatial effects. This study benchmarks GeoShapley—a game‑theoretic explainer treating all location features as a single joint player—against eleven TorchSpatial encoders on a synthetic process with known coefficients, across grid, county, and global scales, with and without raw coordinates and under different training regimes. The results show that primary coefficient recovery is consistently high across encoders, while secondary coefficient recovery varies more with scale, especially at the global level, and raw‑coordinate baselines remain competitive throughout.