Exploring the Long Short-Term Dependencies to Infer Shot Influence in Badminton Matches
This work addresses a domain-specific problem for badminton analysts by providing an interpretable model, but it is incremental as it applies existing deep learning techniques to a new sport.
The paper tackles the problem of identifying significant shots in badminton rallies to evaluate player performance by proposing a deep learning model that predicts rally results, and it demonstrates that the model outperforms strong baselines on a real-world dataset.
Identifying significant shots in a rally is important for evaluating players' performance in badminton matches. While there are several studies that have quantified player performance in other sports, analyzing badminton data is remained untouched. In this paper, we introduce a badminton language to fully describe the process of the shot and propose a deep learning model composed of a novel short-term extractor and a long-term encoder for capturing a shot-by-shot sequence in a badminton rally by framing the problem as predicting a rally result. Our model incorporates an attention mechanism to enable the transparency of the action sequence to the rally result, which is essential for badminton experts to gain interpretable predictions. Experimental evaluation based on a real-world dataset demonstrates that our proposed model outperforms the strong baselines. The source code is publicly available at https://github.com/yao0510/Shot-Influence.