AI for Sports
This talk will explore how computer vision and multimodal AI can help us understand sports, using football as a central example.
Overview
I will discuss my work leading SoccerNet as a platform for benchmarking and challenges in sports video understanding, developing practical tools through OpenSportsLib, and directing the FIFA Research Institute at KAUST. Together, these efforts connect research, evaluation, and real-world applications. The talk will also touch on challenges such as understanding long videos, tracking players and the ball, interpreting actions and interactions, and extending analysis to 3D.
Presenters
Brief Biography
Silvio Giancola is a Research Scientist at KAUST, where he leads initiatives at the intersection of computer vision, artificial intelligence, and sports. He co-founded the SoccerNet project, a large-scale benchmark for soccer video understanding now adopted by hundreds of research groups worldwide. His research spans video understanding, 3D perception, and sports analytics, with applications ranging from athlete biomechanics to broadcast automation. Dr. Giancola has published more than 25 peer-reviewed papers, co-authored a book on 3D camera technologies, and organized workshops and challenges at premier conferences such as CVPR. At KAUST, he plays a central role in the newly established FIFA Research Institute, collaborating with FIFA and industry partners to translate cutting-edge AI research into real-world football solutions.
