A topic model approach to represent and classify american football plays

We address the problem of modeling and classifying American Football offense teams' plays in video, a challenging example of group activity analysis. Automatic play classification will allow coaches to infer patterns and tendencies of opponents more efficiently, resulting in better strategy planning in a game. We define a football play as a unique combination of player trajectories. We develop a framework that uses player trajectories as inputs to MedLDA, a supervised topic model. The joint maximization of both likelihood and inter-class margins of MedLDA in learning the topics allows us to learn semantically meaningful play type templates, as well as, classify different play types with 70% average accuracy. Furthermore, this method is extended to analyze individual player roles in classifying each play type. We validate our method on a large dataset comprising 271 play clips from real-world football games, which will be made publicly available for future comparisons.