One day and four tracks. Computer vision fills the morning, AI infrastructure follows after lunch, and the day finishes with commercialization and then governance, ethics and standards, before a welcome cocktail at 18:00.
| Time | Session |
|---|---|
| 10:00 | Welcome Anselm Küchle, International Football Institute |
| 10:10 | From Event Data to Skeletal Tracking Data: Building Open-Source Infrastructure for Football Analytics Pieter Robberechts, KU Leuven |
| 10:40 | Computer Vision at League Scale: Delivery, Latency and Applications Hendrik Weber, DFL |
| 11:25 | Coffee |
| 11:45 | Selected abstract presentations From the call for abstracts |
| 12:15 | Computer Vision Beyond the Laboratory: Broadcast Video and Fixed Cameras in Club Practice Speakers to be announced |
| 13:00 | Lunch |
| 13:30 | Football Match Analysis: Validity of Performance Indicators in Times of AI Daniel Link, TUM |
| 14:00 | From Validation to Practice: Translating Sports Technology into Applied Use Stefan Altmann, TSG Research Lab |
| 14:30 | Data Ownership and Architecture in the Age of Language Models Speakers to be announced |
| 15:15 | Coffee |
| 15:35 | The European Sports Funding Map: Fundraising Strategies for Sports Technology Ventures Juan Fuentes and Audra Shallal, EBAN Sports |
| 16:15 | Accountability in AI for Sport: Ethical Responsibility When Automated Systems Err Alberto Carrio Sampedro, UPF Barcelona |
| 16:45 | Open floor |
| 17:05 | Close |
| 18:00 | Welcome cocktail Included in the MIDAS ticket |
Computer vision has left the laboratory. At the 2026 World Cup the semi-automated offside system tracks 29 points on every player fifty times a second, and the same technology now feeds broadcast, officiating and performance analysis. The track asks what a club can run week to week from broadcast feeds or a few fixed cameras, and where the data is reliable enough to act on.
Pieter Robberechts of KU Leuven traces the path from event data to 3D skeletal tracking data and argues that open source infrastructure is what moves new data sources from the lab into club practice. Hendrik Weber of the DFL joins a discussion on computer vision from the league's point of view. The remaining slots go to selected abstracts.
Every club holds tracking, event, physical and medical data from several providers, usually in systems never designed to talk to each other. That architecture decides whether AI is useful to a coach on a Tuesday. The track covers what a club has to build first: who owns the data, where it lives and how it moves.
Professor Daniel Link of TUM asks how valid performance indicators in football match analysis remain in times of AI. Stefan Altmann of the TSG Research Lab traces the path from research and scientific validation to practical application, using Helix Arena, Sonic Bone and a talent selection model that estimates a player's probability of progressing and supports what-if analyses.
The money in sports technology is real and uneven. SportsTechX counted about 12.5 billion dollars in disclosed deal flow through October 2025, but the share for athlete and performance solutions fell to 18 percent against a five-year average of 31 percent. The track covers the path from research to product to buyer: what gets procured, why pilots stall and what investors still active in performance and data are looking for.
Juan Fuentes and Audra Shallal of EBAN Sports give an investor reality check.
The EU AI Act applies a risk-based classification that reaches biometric monitoring and automated decisions about people. Player unions have issued their own data protection guidelines, and most agreements still never define who owns athlete data. The closing track asks whether the tools are trustworthy, fair and interoperable at scale, and who is responsible when a model gets it wrong.
Alberto Carrio Sampedro of UPF Barcelona speaks on the ethics of AI in sport.
Partners get fifteen minutes on stage inside the programme, in front of a room that is small enough to follow up with everyone afterwards. The partners page explains the ways to partner.