论文标题
通过空间时间图卷积网络预测团队绩效
Predicting Team Performance with Spatial Temporal Graph Convolutional Networks
论文作者
论文摘要
本文提出了一种从一组代理商的行为痕迹中预测团队绩效的新方法。这个时空预测问题与体育分析挑战（例如教练和对手建模）非常相关。我们证明了我们提出的模型，“空间时间图卷积网络”（ST-GCN），优于其他分类技术，可以从玩家运动和游戏功能的短段预测游戏得分。我们提出的体系结构使用图形卷积网络来捕获团队成员与封闭式复发单元之间的空间关系，以分析动态运动信息。进行了消融性评估，以证明我们体系结构各个方面的贡献。
This paper presents a new approach for predicting team performance from the behavioral traces of a set of agents. This spatiotemporal forecasting problem is very relevant to sports analytics challenges such as coaching and opponent modeling. We demonstrate that our proposed model, Spatial Temporal Graph Convolutional Networks (ST-GCN), outperforms other classification techniques at predicting game score from a short segment of player movement and game features. Our proposed architecture uses a graph convolutional network to capture the spatial relationships between team members and Gated Recurrent Units to analyze dynamic motion information. An ablative evaluation was performed to demonstrate the contributions of different aspects of our architecture.
