发表机构
The University of Tennessee, Knoxville; Oak Ridge National Laboratory（田纳西大学诺克斯维尔分校; 橡树岭国家实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TEMPEST提出基于ArcFace损失的时间卷积网络嵌入模型，将驾驶数据映射为96维嵌入，在45名驾驶员数据集上实现91.71%的Rank-1准确率，显著优于三元组损失基线，并支持无需重训练的动态注册，为可扩展驾驶员识别提供稳健基线。
AI 中文摘要
可扩展的驾驶员识别需要嵌入模型在车队规模增长时保持判别性能，然而现有的三元组损失公式在驾驶员池规模增大时性能迅速下降，并在严格的时间评估下过度拟合会话特定模式。我们提出TEMPEST，一种使用加性角度间隔（ArcFace）损失训练的时间卷积网络嵌入模型，该损失在归一化角度空间中强制实现全局类别级分离。TEMPEST将60秒的多模态驾驶窗口映射为紧凑的96维嵌入，支持真正的动态注册，无需任何重新训练或分类器重拟合。在包含45名驾驶员的数据集上进行严格的时间评估，TEMPEST实现了91.71%的Rank-1准确率，比最佳经典模型高出17.9个百分点，比最强的三元组损失基线高出58.4个百分点。当受试者池从10名驾驶员增加到45名时，TEMPEST仅下降4.3个百分点，而监督和无监督三元组损失基线分别下降22和32.5个百分点。其跨会话优势在公开的KIA Soul数据集上得到证实，在该数据集上，TEMPEST在会话内和跨会话分别比最佳经典模型高出7.3和14.3个百分点。凭借720K参数、2.80 MB大小和50轮收敛，TEMPEST为可扩展的行为驾驶员生物特征识别建立了严格、可复现的基线。
英文摘要
Scalable driver identification requires embedding models that maintain discriminative performance as fleet size grows, yet existing triplet-loss formulations degrade rapidly with driver pool size and overfit to session-specific patterns under rigorous temporal evaluation. We introduce TEMPEST, a Temporal Convolutional Network embedding model trained with an additive angular margin (ArcFace) loss that enforces global class-level separation in a normalized angular space. TEMPEST maps 60-second multimodal driving windows to compact 96-dimensional embeddings, supporting truly dynamic enrollment without any retraining or classifier refitting. Under rigorous temporal evaluation on a 45-driver dataset, TEMPEST achieves 91.71% Rank-1 accuracy, outperforming the best classical model by 17.9 pp and the strongest triplet-loss baseline by 58.4 pp. TEMPEST degrades by only 4.3 pp when growing the subject pool from 10 to 45 drivers, compared to 22 pp and 32.5 pp for supervised and unsupervised triplet-loss baselines, and its cross-session advantage is corroborated on the public KIA Soul dataset, where it outperforms the best classical model by 7.3 pp within-session and 14.3 pp cross-session. With 720K parameters, a 2.80 MB footprint, and 50-epoch convergence, TEMPEST establishes a rigorous, reproducible baseline for scalable behavioral driver biometric identification.
