通过细粒度提示解锁视觉语言模型以用于视频异常检测
Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting
AI总结：
针对现有视频异常检测提示过于抽象的问题，提出结构化提示框架ASK-Hint，通过动作中心知识和细粒度引导问题提升冻结VLM推理准确性与可解释性，在多个基准上取得SOTA且泛化性强。
摘要：
提示已成为适配冻结视觉语言模型（VLM）以用于视频异常检测（VAD）的实用方法。然而，现有提示往往过于抽象，忽略了定义监控视频中复杂异常的细粒度人-物交互或动作语义。我们提出ASK-Hint，这是一个结构化提示框架，利用以动作为中心的知识从冻结VLM中引出更准确且可解释的推理。我们的方法将提示组织成语义连贯的组（如暴力、财产犯罪、公共安全），并制定细粒度引导问题，使模型预测与判别性视觉线索对齐。在UCF-Crime和XD-Violence上的大量实验表明，ASK-Hint的AUC持续优于现有基线，与微调方法和免训练方法相比均达到了最先进的性能。除了准确性之外，我们的框架还提供了针对异常的可解释推理轨迹，并在不同数据集和VLM骨干网络上展现出强泛化性。这些结果凸显了提示粒度的关键作用，并确立了ASK-Hint作为可解释视频异常检测的新型免训练且可泛化的解决方案。
英文摘要：
Prompting has emerged as a practical way to adapt frozen vision-language models (VLMs) for video anomaly detection (VAD). Yet, existing prompts are often overly abstract, overlooking the fine-grained human-object interactions or action semantics that define complex anomalies in surveillance videos. We propose ASK-Hint, a structured prompting framework that leverages action-centric knowledge to elicit more accurate and interpretable reasoning from frozen VLMs. Our approach organizes prompts into semantically coherent groups (e.g. violence, property crimes, public safety) and formulates fine-grained guiding questions that align model predictions with discriminative visual cues. Extensive experiments on UCF-Crime and XD-Violence show that ASK-Hint consistently improves AUC over prior baselines, achieving state-of-the-art performance compared to both fine-tuned and training-free methods. Beyond accuracy, our framework provides interpretable reasoning traces towards anomaly and demonstrates strong generalization across datasets and VLM backbones. These results highlight the critical role of prompt granularity and establish ASK-Hint as a new training-free and generalizable solution for explainable video anomaly detection.
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。
