用人体动作嵌入和轻量时序模型预测足球点球方向，提升守门员反应速度。
MambaKick: Early Penalty Direction Prediction from HAR Embeddings
- 基于预训练动作识别嵌入，结合Mamba模型捕捉时序特征
- 三类方向预测达53.1%准确率，两类达64.5%
- 适合低延迟体育视频意图预测场景，可复用于其他运动
足球点球决策时间极短，守门员若能提前从踢球者动作中预判射门方向则更具优势。本文提出MambaKick，一种基于学习的点球方向预测框架，利用接触中心短片段视频提取的预训练人体动作识别（HAR）嵌入，并与轻量级时序预测器结合。该方法不依赖显式运动学重建或手工生物力学特征，而是复用可迁移的时空表征，采用选择性状态空间模型（Mamba）实现高效序列聚合。同时引入场地方向、脚部偏好等简单上下文元数据作为补充线索，以降低真实视频中的歧义。在多种HAR骨干网络上，MambaKick均优于或匹配强基准，三分类准确率达53.1%，二分类达64.5%。结果表明，将预训练HAR表示与高效状态空间建模结合，是现实体育视频中低延迟意图预测的可行路径。代码将开源至GitHub：https://github.com/hvelesaca/MambaKick/
原文摘要 · Abstract (English)
Penalty kicks in soccer are decided under extreme time constraints, where goalkeepers benefit from anticipating shot direction from the kickers motion before or around ball contact. In this paper, MambaKick is presented as a learning-based framework for penalty direction prediction that leverages pretrained human action recognition (HAR) embeddings extracted from contact-centered short video segments and combines them with a lightweight temporal predictor. Rather than relying on explicit kinematic reconstruction or handcrafted biomechanical features, the approach reuses transferable spatiotemporal representations and utilizes selective state-spare models (Mamba) for efficient sequence aggregation. Simple contextual metadata (e.g., field side and footedness) are also considered as complementary cues that may reduce ambiguity in real-world footage. Across a range of HAR backbones, MambaKick consistently improves or matches strong embedding baselines, achieving up to 53.1% accuracy for three classes and 64.5% for two classes under the proposed methodology. Overall, the results indicate that combining pretrained HAR representations with efficient state-space temporal modeling is a practical direction for low-latency intention prediction in real-world sports video. The code will be available at GitHub: https://github.com/hvelesaca/MambaKick/
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。