This class is a graduate course in machine learning for Sport Analytics.
Prerequisites: A good knowledge of statistics, linear algebra, calculus and machine learning is necessary as well as good programming skills. A good knowledge of computer vision is strongly recommended.
Each student will need to compete on 2/3 challenges, present once or twice in class (depending on enrollment), participate in class discussions, complete a project (which could be a challenge done individually or in pairs) and do the quizzes.
The final grade will consist of the following | |
---|---|
Presentation (presentation of papers in class) | 10% |
Quizzes (solving some sport analytics tasks) | 25% |
Challenges (competing in 2/3) | 40% |
Project (final report, presentation) | 25% |
Depending on enrollment, each student will need to present a few papers in class. The presentation should be clear and practiced and the student should read the assigned paper and related work in enough detail to be able to lead a discussion and answer questions. Extra credit will be given to students who also prepare a simple experimental demo highlighting how the method works in practice. In the presentation, also provide the citation to the papers you present and to any other related work you reference
Deadline: The presentation should be handed in one day before the class (or before if you want feedback).
Structure of presentation: |
---|
High-level overview with contributions |
Main motivation |
Clear statement of the problem |
Overview of the technical approach |
Strengths/weaknesses of the approach |
Overview of the experimental evaluation |
Strengths/weaknesses of evaluation |
Discussion: future direction, links to other work |
Projects can be done in pairs or individually. Students can use a challenge as their project, or choose a different topic. The grade will depend on the ideas, how well you present them in the report, how well you position your work in the related literature, how thorough are your experiments and how thoughtful are your conclusions.
Coming soon
Choose 2 out of the following 3 challenges | |
---|---|
Challenge 1 Detection and tracking | Due end of class |
Challenge 2 Unsupervised learning | Due end of class |
Challenges 3 Bracketology | Due March 11th |
Date | Topic | Readings | Presenters | Slides |
---|---|---|---|---|
Jan 9 | Introduction | Raquel Urtasun | intro | |
Jan 16 | Intro to Convolutional Nets | Bin Yang | Conv Nets | |
Jan 23 | Intro to RNNs | Mengye Ren | RNNs | |
Jan 30 | Intro to Generative Models | Shenlong Wang | Generative Models | |
Feb 6 | Intro to Field Localization | Namdar Homayounfar | Field Localization | |
Feb 13 | Intro to Object Detection | Bin Yang | Object Detection | |
Feb 27 | Player Tracking |
Global Data Association for Multi-Object Tracking Using Network Flows CVPR 2008 [PDF] L. Zhang and R. Nevatia Multiple Object Tracking using K-Shortest Paths Optimization PAMI 2011 [PDF] J. Berclaz, F. Fleuret, E. Turetken, and P. Fua Multi-target tracking by discrete-continuous energy minimization PAMI 2016 [PDF] A. Milan, K. Schindler, S. Roth | Davi Frossard | Player Tracking |
Feb 27 | Play Recognition |
Classifying NBA Offensive Plays Using Neural Networks MIT SLOAN 2016 [PDF] K. Wang and R. Zemel | Jackson Wang | Play Recognition |
March 6 | Play, player and defense Recognition |
Generating Long-term Trajectories Using Deep Hierarchical Networks NIPS 2016 [PDF] S. Zheng, Y. Yue and J. Hobbs Counterpoints: Advanced Defensive Metrics for NBA Basketball MIT SLOAN 2015 [PDF] A. Franks, A. Miller, L. Bornn and K. Goldsberry Characterizing the spatial structure of defensive skill in professional basketball Annals of Applied Statistics 2015 [PDF] A. Franks, A. Miller, Luke Bornn and K. Goldsberry Predicting Points and Valuing Decisions in Real Time with NBA Optical Tracking Data MIT SLOAN 2014 [PDF] D. Cervone, A. D'Amourt, L. Bornn and K. Goldsberry A Multiresolution Stochastic Process Model for Predicting Basketball Possession Outcomes Journal Of The American Statistical Association 2016 [PDF] D. Cervone, A. D'Amourt, L. Bornn and K. Goldsberry | Jackson Wang | PPD Recognition |
March 13 | Ball Tracking |
Take your Eyes off the Ball:
Improving Ball-Tracking by Focusing onTeam Play CVIU 2013 [PDF] X. Wang, V. Ablavsky, H. Ben Shitrit and P. Fua What Players do with the Ball: A Physically Constrained Interaction Modeling Optimization CVPR 2016 [PDF] A. Maksai, X. Wang and P. Fua | TBD | Ball Tracking |
March 13 | Activity Recognition |
Detecting events and key actors in multi-person videos CVPR 2016 [PDF] V. Ramanathan, J. Huang, S. Abu-El-Haija, A. Gorban, K. Murphy, Li Fei-Fei | TBD | Activity Recognition |
March 20 | Automatic Filming of Sports |
Learning Online Smooth Predictors for Realtime Camera Planning
using Recurrent Decision Trees CVPR 2016 [PDF] J. Chen, H. M. Le, P. Carr, Y. Yue and J. Little | TBD | Automatic Filming |