Analytics in professional sports has experienced a dramatic growth in the last decade due to
the wide deployment of player and ball tracking systems in team sports, such as basketball
and soccer. With the massive amount of fine-grained data being generated, new data-points
are being generated, which can shed light on player and team performance. However, due
to the complexity of plays in continuous sports, these data-points often lack the specificity
and context to enable meaningful retrieval and analytics. In this article, we present an …

Fig. 1.(a) Conventional methods for sports play access are based on “keywords”, which lack
specificity and requires the user to browse through a large collection before finding the
specific plays of interest.(b) To improve retrieval e ectiveness, we instead use trajectories,
which is an intuitive and powerful query format that allows the user to specify plays similar to
how a coach/analyst draws up plays, and can capture the rich semantics required for e
ective sports play retrieval.(c) An alternative method of drawing up plays could also be on a …