Lessons & Papers

Helpful lessons of Sports Analytics and interesting research papers published on important AI conference and MIT Slogan Sports Analytics Conference. I also add some researchers who are pioneers to sports analytics.


CSC2541 is a graduate course in machine learning for Sport Analytics from Toronto University, which contains useful resources.
MIT Slogan Sports Analytics Conference Videos
Here records many of the speeches in MIT Slogan Sports Analytics Conference (SSAC) sicne 2012.

Selected Papers

Tracking data driven
<Data-Driven Ghosting using Deep Imitation Learning>, 2017.
Published on MIT-Slogan Sports Analytics Conference (SSAC). TBA.
<BasketballGAN: Generating Basketball Play Simulation Through Sketching>, 2019.
Published on ACM MultiMedia (ACM MM). TBA.
Statistical data driven
<Actions Speak Louder than Goals: Valuing Player Actions in Soccer>, 2019.
KDD best paper of application track. TBA.
Visual data driven (Mostly Tracking)
<Multiple Object Tracking in Soccer Videos using Topographic Surface Analysis>, 2019.
<Tracking Multiple People in a Multi-Camera Environment>, 2018.
<Soccer: Who Has The Ball? Generating Visual Analytics and Player Statistics>, 2018.
Published on CVPR workshop. TBA.
<A Survey on Player Tracking in Soccer Videos>, 2017.
<A Survey on Content-aware Video Analysis for Sports>, 2017.
<Event Recognition in Broadcast Soccer Videos>, 2016.
Published in ICVGIP16, Proceedings of the Tenth Indian Conference on Computer Vision, Graphics and Image Processing.
<Detecting events and key actors in multi-person videos>
By Google and Stanford researchers (Feifei Li).
<Learning to Track and Identify Players from Broadcast Sports Videos>, 2012.
<Ball Tracking and Action Recognition of Soccer Players in TV Broadcast Videos>, 2007.
This is a theis which detailed describe various methods of Video processing in football analysis. TBA.
<Visually Tracking Football Games Based on TV Broadcasts>, 2007.
Published in IJCAI07. This paper is an extension of <ASPOGAMO: Automated Sports Game Analysis Models>. They propose ASPOGAMO, a visual tracking system that determines the coordinates and trajectories of football players in camera view based on TV broadcasts.
<Players and Ball Detection in Soccer Videos Based on Color Segmentation and Shape Analysis>, 2007.
Published in MCAM 2007. This paper proposes a scheme to detect and locate the players and the ball on the grass playfield in soccer videos.
<Soccer video analysis by ball, player and referee tracking>, 2006.


Patrick Lucey is currently the VP of Artificial Intelligence at STATS, whose research interests cover artificial intelligence and interactive machine learning in sporting domains. Many of his publications which can be found on his webpage coincide with my interests.