Learning Person Trajectory Representations for Team Activity Analysis
This work addresses activity analysis for multiple interacting people in large spaces, such as sports analytics, but is incremental as it applies deep learning to existing datasets.
The paper tackled the challenge of analyzing group activities by learning person trajectory representations that capture spatio-temporal dependencies and motion patterns, enabling recognition of individual events and group dynamics in team sports like NHL hockey and NBA basketball.
Activity analysis in which multiple people interact across a large space is challenging due to the interplay of individual actions and collective group dynamics. We propose an end-to-end approach for learning person trajectory representations for group activity analysis. The learned representations encode rich spatio-temporal dependencies and capture useful motion patterns for recognizing individual events, as well as characteristic group dynamics that can be used to identify groups from their trajectories alone. We develop our deep learning approach in the context of team sports, which provide well-defined sets of events (e.g. pass, shot) and groups of people (teams). Analysis of events and team formations using NHL hockey and NBA basketball datasets demonstrate the generality of our approach.