Guardado en:
Detalles Bibliográficos
Autores principales: Ochin, Jeremie, Chekroun, Raphael, Stanciulescu, Bogdan, Manitsaris, Sotiris
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.09455
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917233773510656
author Ochin, Jeremie
Chekroun, Raphael
Stanciulescu, Bogdan
Manitsaris, Sotiris
author_facet Ochin, Jeremie
Chekroun, Raphael
Stanciulescu, Bogdan
Manitsaris, Sotiris
contents State-of-the-art spatio-temporal action detection (STAD) methods show promising results for extracting soccer events from broadcast videos. However, when operated in the high-recall, low-precision regime required for exhaustive event coverage in soccer analytics, their lack of contextual understanding becomes apparent: many false positives could be resolved by considering a broader sequence of actions and game-state information. In this work, we address this limitation by reasoning at the game level and improving STAD through the addition of a denoising sequence transduction task. Sequences of noisy, context-free player-centric predictions are processed alongside clean game state information using a Transformer-based encoder-decoder model. By modeling extended temporal context and reasoning jointly over team-level dynamics, our method leverages the "language of soccer" - its tactical regularities and inter-player dependencies - to generate "denoised" sequences of actions. This approach improves both precision and recall in low-confidence regimes, enabling more reliable event extraction from broadcast video and complementing existing pixel-based methods.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09455
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos
Ochin, Jeremie
Chekroun, Raphael
Stanciulescu, Bogdan
Manitsaris, Sotiris
Computer Vision and Pattern Recognition
State-of-the-art spatio-temporal action detection (STAD) methods show promising results for extracting soccer events from broadcast videos. However, when operated in the high-recall, low-precision regime required for exhaustive event coverage in soccer analytics, their lack of contextual understanding becomes apparent: many false positives could be resolved by considering a broader sequence of actions and game-state information. In this work, we address this limitation by reasoning at the game level and improving STAD through the addition of a denoising sequence transduction task. Sequences of noisy, context-free player-centric predictions are processed alongside clean game state information using a Transformer-based encoder-decoder model. By modeling extended temporal context and reasoning jointly over team-level dynamics, our method leverages the "language of soccer" - its tactical regularities and inter-player dependencies - to generate "denoised" sequences of actions. This approach improves both precision and recall in low-confidence regimes, enabling more reliable event extraction from broadcast video and complementing existing pixel-based methods.
title Beyond Pixels: Leveraging the Language of Soccer to Improve Spatio-Temporal Action Detection in Broadcast Videos
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.09455