Machine Learning in Sports Postponed
( 26. Apr – 30. Apr, 2020 )
- Ulf Brefeld (Universität Lüneburg, DE)
- Jesse Davis (KU Leuven, BE)
- Martin Lames (TU München, DE)
- Jim Little (University of British Columbia - Vancouver, CA)
- Arne Jaspers (KU Leuven, BE)
- Michael Gerke (für wissenschaftliche Fragen)
Advances in data collection techniques have enabled collecting large amounts of data about sports such as event data (e.g., time and locations of actions), tracking data (i.e., positional data), and athlete monitoring (e.g., bio-sensors, IMUs, GPS). These data are commonly and widely collected across multiple different sports. Even recreational athletes make use of a variety of sensors to monitor their training and performances. The advent of such data raises the need to exploit the collected data both from the theoretical (e.g., sports modeling) as well as practical (e.g., training in top level sports) perspective. Problem-solving solutions can be provided by an interaction between the sports science&informatics (S&I) and the machine learning (ML) communities. Machine learning is emerging as a powerful, new paradigm for sports analytics, as it provides novel approaches to making sense of the collected data. However, the S&I and ML communities are traditionally separate, each with its own agenda. The Dagstuhl Seminar aims to bring together top researchers and practitioners who are active in these two fields that can contribute to an assessment of their potential synergies.
The seminar aims to discuss the following key questions: (i) What challenges arise when analyzing new, and massive amounts of data that are available about sports? (ii) What are the key open problems that require a combination of sports science and machine learning know-how to solve? (iii) How can we best facilitate interaction among computer scientists, sports scientists, and end-users? (iv) How can we foster interdisciplinary collaborations on a regular basis? We plan to discuss these questions along different dimensions, such as different types of data, tactics and strategy, player actions, athlete monitoring, and privacy/dual-use.
The goal of the seminar will be to identify key challenges and opportunities that arise when combining computer science and sport science: joint research can lead to synergies that, ultimately, form the basis for breakthroughs and the connections and ideas formed during the seminar ideally lead to future research projects or publications dealing with interdisciplinary research on making sense of data in sports.
- artificial intelligence / robotics
- computer graphics / computer vision
- machine learning
- computer vision