基于大语言模型的知识引导文本推理用于可解释视频异常检测
Knowledge-Guided Textual Reasoning for Explainable Video Anomaly Detection via LLMs
AI总结：
针对弱监督视频异常检测，提出TbVAD框架，通过视觉语言模型生成细粒度字幕并构建含动作等四语义槽的结构化知识，借助大语言模型推理实现文本域内异常检测与解释，在UCF-Crime和XD-Violence上验证有效性。
摘要：
我们提出了基于文本的可解释视频异常检测（TbVAD），这是一种语言驱动的弱监督视频异常检测框架，可在文本域内完成异常检测和解释。与依赖显式视觉特征的传统WSVAD模型不同，TbVAD通过语言表示视频语义，实现可解释且基于知识的推理。该框架分三阶段运行：（1）使用视觉语言模型将视频内容转化为细粒度字幕；（2）通过将字幕组织为四个语义槽（动作、对象、上下文、环境）构建结构化知识；（3）生成槽级解释，揭示哪些语义因素对异常决策贡献最大。我们在UCF-Crime和XD-Violence两个公开基准上评估TbVAD，表明文本知识推理可为真实世界监控场景提供可解释且可靠的异常检测。
英文摘要：
We introduce Text-based Explainable Video Anomaly Detection (TbVAD), a language-driven framework for weakly supervised video anomaly detection that performs anomaly detection and explanation entirely within the textual domain. Unlike conventional WSVAD models that rely on explicit visual features, TbVAD represents video semantics through language, enabling interpretable and knowledge-grounded reasoning. The framework operates in three stages: (1) transforming video content into fine-grained captions using a vision-language model, (2) constructing structured knowledge by organizing the captions into four semantic slots (action, object, context, environment), and (3) generating slot-wise explanations that reveal which semantic factors contribute most to the anomaly decision. We evaluate TbVAD on two public benchmarks, UCF-Crime and XD-Violence, demonstrating that textual knowledge reasoning provides interpretable and reliable anomaly detection for real-world surveillance scenarios.
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。
