ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton

TL;DR

ShuttleNet is a novel framework for stroke forecasting in badminton that effectively combines rally progress and player styles through position-aware fusion, significantly outperforming existing methods.

Contribution

The paper introduces ShuttleNet, a new position-aware fusion model that incorporates rally and player information for improved stroke prediction in badminton.

Findings

ShuttleNet outperforms state-of-the-art methods on badminton datasets.

Each component of ShuttleNet is empirically validated.

The framework demonstrates the feasibility of position-aware fusion in sports analysis.

Abstract

The increasing demand for analyzing the insights in sports has stimulated a line of productive studies from a variety of perspectives, e.g., health state monitoring, outcome prediction. In this paper, we focus on objectively judging what and where to return strokes, which is still unexplored in turn-based sports. By formulating stroke forecasting as a sequence prediction task, existing works can tackle the problem but fail to model information based on the characteristics of badminton. To address these limitations, we propose a novel Position-aware Fusion of Rally Progress and Player Styles framework (ShuttleNet) that incorporates rally progress and information of the players by two modified encoder-decoder extractors. Moreover, we design a fusion network to integrate rally contexts and contexts of the players by conditioning on information dependency and different positions. Extensive experiments on the badminton dataset demonstrate that ShuttleNet significantly outperforms the state-of-the-art methods and also empirically validates the feasibility of each component in ShuttleNet. On top of that, we provide an analysis scenario for the stroke forecasting problem.