MoCVAE: Movement Prediction by A Conditional Variational Autoencoder for Doubles Badminton

Pei Chieh Sung, Hsu Chao Lai, Guan Yi Jhang, Tsi Ui Ik, Chih Chuan Wang, Jiun Long Huang

研究成果: Conference contribution同行評審

摘要

AI has emerged as a potent tool of sports analysis, but there is no research yet for doubles badminton. In this paper, we introduce a novel movements prediction model, namely MoCVAE, for doubles badminton. MoCVAE differentiates the doubles setting from the singles and leverages its uniqueness to improve performance. Specifically, the Player Position Embedding module is pre-trained with singles data to initialize embeddings to overcome the scarcity of data. On top of a CVAE-based structure, a novel Motion Interaction module further employs a GAT to refine the embeddings based on interaction among the players. Finally, in addition to player movements, MoCVAE simultaneously predicts hitting players and shot types since they are all significantly correlated. The experimental results on real datasets show that MoCVAE outperforms its variants by 61.22% in terms of ADE, manifesting that MoCVAE integrates all the essential perspectives successfully.

原文English
主出版物標題Proceedings - 2024 IEEE International Conference on Big Data and Smart Computing, BigComp 2024
編輯Herwig Unger, Jinseok Chae, Young-Koo Lee, Christian Wagner, Chaokun Wang, Mehdi Bennis, Mahasak Ketcham, Young-Kyoon Suh, Hyuk-Yoon Kwon
發行者Institute of Electrical and Electronics Engineers Inc.
頁面40-47
頁數8
ISBN(電子)9798350370027
DOIs
出版狀態Published - 2024
事件2024 IEEE International Conference on Big Data and Smart Computing, BigComp 2024 - Bangkok, Thailand
持續時間: 18 2月 202421 2月 2024

出版系列

名字Proceedings - 2024 IEEE International Conference on Big Data and Smart Computing, BigComp 2024

Conference

Conference2024 IEEE International Conference on Big Data and Smart Computing, BigComp 2024
國家/地區Thailand
城市Bangkok
期間18/02/2421/02/24

指紋

深入研究「MoCVAE: Movement Prediction by A Conditional Variational Autoencoder for Doubles Badminton」主題。共同形成了獨特的指紋。

引用此