TAU-R1：用于交通异常理解的视觉语言模型
TAU-R1: Visual Language Model for Traffic Anomaly Understanding
AI总结：
本文提出TAU-R1模型，通过两层框架提升交通异常识别与推理能力，结合定制化训练策略与数据集，实现高效部署。
摘要：
交通异常理解（TAU）对于智能交通系统中的交通安全至关重要。尽管最近的视觉语言模型（VLMs）在视频理解方面表现出色，但TAU进展有限，主要是由于缺乏基准和任务特定的方法。为此，我们引入Roundabout-TAU数据集，包含342个片段和超过2000个问题-答案对，覆盖交通异常理解的多个方面。基于此基准，我们提出了TAU-R1，一个两层视觉语言框架。第一层是轻量级异常分类器，用于粗粒度异常分类；第二层是更大的异常推理器，生成详细事件摘要。为提高任务特定推理能力，我们引入了两阶段训练策略，包括分解QA增强的监督微调，随后是基于GRPO的后训练方法，结合TAU特定的奖励函数。实验结果表明，TAU-R1在异常分类和推理任务中表现优异，同时保持了部署效率。数据集和代码可在https://github.com/siri-rouser/TAU-R1获取。
英文摘要：
Traffic Anomaly Understanding (TAU) is important for traffic safety in Intelligent Transportation Systems. Recent vision-language models (VLMs) have shown strong capabilities in video understanding. However, progress on TAU remains limited due to the lack of benchmarks and task-specific methodologies. To address this limitation, we introduce Roundabout-TAU, a dataset constructed from real-world roundabout videos collected in collaboration with the City of Carmel, Indiana. The dataset contains 342 clips and is annotated with more than 2,000 question-answer pairs covering multiple aspects of traffic anomaly understanding. Building on this benchmark, we propose TAU-R1, a two-layer vision-language framework for TAU. The first layer is a lightweight anomaly classifier that performs coarse anomaly categorisation, while the second layer is a larger anomaly reasoner that generates detailed event summaries. To improve task-specific reasoning, we introduce a two-stage training strategy consisting of decomposed-QA-enhanced supervised fine-tuning followed by TAU-GRPO, a GRPO-based post-training method with TAU-specific reward functions. Experimental results show that TAU-R1 achieves strong performance on both anomaly classification and reasoning tasks while maintaining deployment efficiency. The dataset and code are available at: https://github.com/siri-rouser/TAU-R1
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
