发表机构
The Hong Kong Polytechnic University（香港理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TrajMind是一种快慢结合的框架，通过角色专用LoRA实现群体轨迹异常诊断，慢路径TrajMind_slow性能优于基线，快路径TrajMind_fast延迟低且准确率高，可用于城市交通治理。
AI 中文摘要
从城市轨迹中诊断群体异常对交通治理愈发重要，因为它能揭示发生了什么、涉及谁以及事件发生的时间和地点。现有检测器能高效生成分数或标签，而视觉-语言流水线能提供更丰富的语义；但二者均未将可验证的诊断与低延迟监控结合起来。核心挑战在于，无需为每个监控窗口运行完整诊断流水线，就能识别群体模式并从源轨迹中恢复精确的事件细节。因此，我们将持续在线筛查与按需诊断分开：筛查发出警报，而诊断仅发布经源验证的“什么-谁-何时-何地”记录。我们提出TrajMind，这是一种快慢结合的框架，在一个冻结的视觉-语言主干上切换三个角色专用LoRA适配器。其慢路径TrajMind_slow将基于画布的分类、基于类型的序列化轨迹定位以及可执行验证串联起来，产生结构化、有证据支持的诊断。此外，快路径TrajMind_fast以仅文本的单次传递筛查每个窗口，提供高效的结构化警报。大量实验表明，TrajMind_slow在异常分类上优于最强基线至少15.3个百分点，在定位上优于最强基线至少13.8个百分点。这些优势在跨城市迁移时依然存在，且TrajMind_fast将延迟降低了41.1%，并保持至少93.5%的二元平衡准确率。总体而言，TrajMind可在不同城市提供准确、有证据支持的诊断，并实现高效的一线监控。
英文摘要
Diagnosing collective anomalies from urban trajectories is increasingly important for traffic governance, as it reveals what happened, who was involved, and where and when the event occurred. Existing detectors efficiently produce scores or labels, whereas vision--language pipelines provide richer semantics; neither couples verifiable diagnosis with low-latency monitoring. The central challenge is to recognize collective patterns and recover exact event details from the source trajectories without running the full diagnostic pipeline for every monitored window. We therefore separate always-on screening from on-demand diagnosis: screening raises alerts, while diagnosis releases only source-verified what--who--where--when records. We present TrajMind, a fast-and-slow framework that switches three role-specialized LoRA adapters over one frozen vision--language backbone. Its slow path, \textit{TrajMind$_{\text{slow}}$}, chains canvas-based typing, type-conditioned localization over serialized trajectories, and executable verification, yielding structured, evidence-backed diagnoses. Additionally, the fast path, \textit{TrajMind$_{\text{fast}}$}, screens each window in a single text-only pass, delivering efficient structured alerts. Extensive experiments show that, TrajMind$_{\mathrm{slow}}$ outperforms the strongest baselines by at least $15.3$ percentage points in anomaly typing and $13.8$ percentage points in localization. These gains persist under cross-city transfer, and TrajMind$_{\mathrm{fast}}$ reduces latency by $41.1\%$ and maintains binary balanced accuracy of at least $93.5\%$. Together, TrajMind delivers accurate, evidence-backed diagnoses across cities and efficient front-line monitoring.
