# SoccerMaster: A Vision Foundation Model for Soccer Understanding

arXiv: https://arxiv.org/abs/2512.11016 · HTML: https://mlsanity.com/paper/2512.11016/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 93 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 30 of 69)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking](https://mlsanity.com/paper/1609.01775/) (2016)
- [HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking](https://mlsanity.com/paper/2009.07736/) (2020)
- [Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking](https://mlsanity.com/paper/2203.14360/) (2022)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos](https://mlsanity.com/paper/1804.04527/) (2018)
- [Leapfrog Diffusion Model for Stochastic Trajectory Prediction](https://mlsanity.com/paper/2303.10895/) (2023)
- [SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos](https://mlsanity.com/paper/2011.13367/) (2020)
- [SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes](https://mlsanity.com/paper/2304.05170/) (2023)
- [FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality Assessment](https://mlsanity.com/paper/2204.03646/) (2022)
- [Hierarchical Deep Temporal Models for Group Activity Recognition](https://mlsanity.com/paper/1607.02643/) (2016)

## Built on by (most cited first, 10 of 10)

- [GenTac: Generative Modeling and Forecasting of Soccer Tactics](https://mlsanity.com/paper/2604.11786/) (2026)
- [VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization](https://mlsanity.com/paper/2602.09934/) (2026)
- [Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching](https://mlsanity.com/paper/2603.18453/) (2026)
- [Towards Athlete Fatigue Assessment from Association Football Videos](https://mlsanity.com/paper/2604.05636/) (2026)
- [Towards Temporal Compositional Reasoning in Long-Form Sports Videos](https://mlsanity.com/paper/2604.22226/) (2026)
- [SoccerLens: Grounded Soccer Video Understanding Beyond Accuracy](https://mlsanity.com/paper/2605.09598/) (2026)
- [SoccerNet 2026 Challenges Results](https://mlsanity.com/paper/2607.07320/) (2026)
- [BasketEvent: Understanding Who Did What and When in Basketball Videos](https://mlsanity.com/paper/2607.21267/) (2026)
- [SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning](https://mlsanity.com/paper/2608.07932/) (2026)
- [StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary](https://mlsanity.com/paper/2608.19723/) (2026)

## Abstract (arXiv)

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.