Chalkboarding: A New Spatiotemporal Query Paradigm for Sports Play Retrieval

 

We showcase the efficacy of our approach in a user study, where we demonstrate orders-of-magnitude improvements in search quality compared to baseline systems

March 7, 2016
Intelligent User Interfaces (IUI) 2016

 

Authors

Long Sha (Queensland University of Technology)

Patrick Lucey (Disney Research)

Yisong Yue (California Institute of Technology)

Peter Carr (Disney Research)

Charlie Rohlf (STATS LLC)

Iain Matthews (Disney Research)

Chalkboarding: A New Spatiotemporal Query Paradigm for Sports Play Retrieval

Abstract

The recent explosion of sports tracking data has dramatically increased the interest in effective data processing and access of sports plays (i.e., short trajectory sequences of players and the ball). And while there exist systems that offer improved categorizations of sports plays (e.g., into relatively coarse clusters), to the best of our knowledge there does not exist any retrieval system that can effectively search for the most relevant plays given a specific input query. One significant design challenge is how best to phrase queries for multi-agent spatiotemporal trajectories such as sports plays. We have de- veloped a novel query paradigm and retrieval system, which we call Chalkboarding, that allows the user to issue queries by drawing a play of interest (similar to how coaches draw up plays). Our system utilizes effective alignment, templating, and hashing techniques tailored to multi-agent trajectories, and achieves accurate play retrieval at interactive speeds. We showcase the efficacy of our approach in a user study, where we demonstrate orders-of-magnitude improvements in search quality compared to baseline systems.

Copyright Notice