通过双向击球上下文融合，提升羽毛球击球分类准确率
TemPose-TF-ASF: Two-Stage Bidirectional Stroke Context Fusion for Badminton Stroke Classification
- 分两阶段利用前后击球信息构建上下文
- 在大规模数据集上准确率与宏平均F1显著提升
- 可无缝集成到现有模型，适用性强
精准的羽毛球击球预测对精细化运动分析和战术决策至关重要。然而，现有方法难以建模丰富的时序上下文。本文提出TemPose-TF-ASF（相邻击球融合）方法，作为TemPose的上下文感知扩展，通过融合前序与后序击球类型信息增强击球识别能力。采用两阶段训练与推理策略：先用基线模型生成初步预测作为估计的时序上下文，再联合优化ASF模块与分类器。通过显式建模双向时序击球依赖关系，该方法可无缝集成至现有先进模型中。在大规模羽毛球比赛数据集上的实验表明，其在准确率和宏平均F1上均优于基线及其变体；同时，将ASF集成至其他先进方法也带来显著性能提升，证明了其优异的迁移性与泛化能力。
原文摘要 · Abstract (English)
Accurate badminton stroke prediction is crucial for fine-grained sports analysis and tactical decision support. However, existing methods struggle to model rich temporal context. This paper introduces TemPose-TF-ASF (Adjacent-Stroke Fusion), a context-aware extension of TemPose. It enhances stroke recognition by incorporating stroke-type information from both preceding and subsequent strokes. A two-stage training and inference strategy is adopted. Preliminary predictions from the baseline model are reused as estimated temporal context. These predictions guide the joint optimization of the ASF module and the classifier. By explicitly modeling bidirectional temporal stroke dependencies, the proposed method can be seamlessly integrated into existing state-of-the-art models. Experiments on a large-scale badminton match dataset show consistent improvements over the baseline and its variants in terms of Accuracy and Macro-F1. Moreover, integrating ASF into other advanced methods yields notable performance gains. These results demonstrate strong transferability and generalization capability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。