Large-Scale Analysis of Formations in Soccer

Large-Scale Analysis of Soccer Matches Using Spatiotemporal Tracking Data

“…This type of approach was used to discover how teams achieved open three-point shots in basketball [29]. Bialkowski et al [30] also used a similar approach to investigate the home advantage in soccer, and Wei et al [31] used it to cluster different methods of how teams scored a goal. Although these works all align the multiagent data is some form, our work differs as we learn this alignment directly from the data.…”

Learning Fine-Grained Spatial Models for Dynamic Sports Play Prediction

“…Due to these challenges, most previous work in sports analytics have focused on relatively small datasets [14], [15], [16], did not build predictive models [17], [8], [18], used coarse aggregate statistics that do not model specific in-game scenarios [19], did not focus on adversarial team environments [20], do not model spatial information [21], [22], or require extensive manual annotation [5]. In contrast, we are interested in making in-game predictions of near-term events over a large selection of adversarial in-game scenarios.…”

Injury Mechanism Classification in Soccer Videos

“…Automatic detection of such events can alleviate this burden and help coaches to focus on higher-level tasks such as strategy analysis. Wei et al [22] proposed a twolayer hierarchical approach to detect events such as in-play (when the match being played), stoppage (when the ball is out, fouls, player injury, substitution, etc. ), out-for-corners, out-for-goal-kicks, Foul Freekicks and Out-for-throw-in.…”