Metraipolis › archive › dc_c60d8a55ebd7
Does 3D Pose Improve Action Valuation in Football? An Empirical Study of Pose Representations and Learning Objectives — arXiv:2610.38308
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38308
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:26:58.242Z
- SHA-256 of the archived text
bad138e8591e8eb79eb58f3a6a958af48f7fc3ca8993a2c565c04b7789d8949f- Stable URL of this page
https://metraipolis.com/documento/dc_c60d8a55ebd7
How to cite
Does 3D Pose Improve Action Valuation in Football? An Empirical Study of Pose Representations and Learning Objectives — arXiv:2610.38308 — arXiv (en), https://arxiv.org/abs/2610.38308 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c60d8a55ebd7 (Metraipolis archive dc_c60d8a55ebd7, sha256 bad138e8591e8eb79eb58f3a6a958af48f7fc3ca8993a2c565c04b7789d8949f)
BibTeX
@misc{dcc60d8a55ebd7,
title = {Does 3D Pose Improve Action Valuation in Football? An Empirical Study of Pose Representations and Learning Objectives — arXiv:2610.38308},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38308},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c60d8a55ebd7; sha256 bad138e8591e8eb79eb58f3a6a958af48f7fc3ca8993a2c565c04b7789d8949f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38308. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Football action valuation estimates players' contributions to future scoring. Existing multi-agent deep reinforcement learning (MADRL) models use 2D positions and velocities, omitting posture information relevant to imminent actions. We investigate whether adding 3D pose to a SARSA-based model improves observed-action values relative to attack returns: goals, conceded goals or final expected possession value. Using UEFA Champions League 2022/23 event, tracking and 3D pose data, we compare six representations (no pose, raw joints, torso and head orientation, and spatial-temporal graph convolutional network (ST-GCN) embeddings) across five learning settings and three seeds. The settings vary temporal-difference targets and action-prediction loss, with Monte Carlo return regression as a reference. Across 50 on-ball and off-ball comparisons, pose robustly improved return prediction in only three, all using torso and head orientation, while worsening it in twelve, mostly with ST-GCN. Training choices had greater effects: removing the action-prediction loss raised on-ball skill of position-only values from 0.003 to 0.040 and their correlation with expected goals from 0.23 to 0.60; the improvement in return prediction persisted at matched training length. Separately, pose improved prediction of the on-ball action 0.2 s ahead (macro AUC 0.914 to 0.934 with raw joints), while the passer's pose during execution improved pass-success prediction (AUC 0.844 to 0.856). Within this training protocol, pose informed imminent actions but rarely improved observed-action values. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.38308 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-01T02:12:44.257Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).