SoccerMaster: A Vision Foundation Model for Soccer Understanding

TL;DR

SoccerMaster is a unified vision foundation model designed for comprehensive soccer understanding, capable of handling diverse tasks from athlete detection to event classification through multi-task pretraining.

Contribution

It introduces SoccerMaster, the first soccer-specific foundation model that unifies multiple tasks, along with an automated data curation pipeline and extensive evaluation showing its superiority.

Findings

SoccerMaster outperforms task-specific models across various soccer understanding tasks.

The SoccerFactory pipeline enables scalable generation of spatial annotations.

The model demonstrates broad applicability and improved performance in soccer video analysis.

Abstract

Soccer understanding has recently garnered growing research interest due to its domain-specific complexity and unique challenges. Unlike prior works that typically rely on isolated, task-specific expert models, this work aims to propose a unified model to handle diverse soccer visual understanding tasks, ranging from fine-grained perception (e.g., athlete detection and identification) to high-level semantic reasoning (e.g., event classification). Concretely, our contributions are threefold: (i) we present SoccerMaster, the first soccer-specific vision foundation model that unifies diverse tasks within a single framework via supervised multi-task pretraining; (ii) we develop an automated data curation pipeline, SoccerFactory, to generate scalable spatial annotations, and integrate multiple existing soccer video datasets as a comprehensive pretraining data resource for multi-task pretraining; and (iii) we conduct extensive evaluations demonstrating that SoccerMaster consistently outperforms task-specific expert models across diverse downstream tasks, highlighting its breadth and superiority. The data, code, and model will be publicly available.