QVAD：一种以问题为中心的代理框架，用于高效且无需训练的视频异常检测
QVAD: A Question-Centric Agentic Framework for Efficient and Training-Free Video Anomaly Detection
AI总结：
QVAD提出一种以问题为中心的代理框架，通过动态对话机制提升视频异常检测的效率和性能，无需参数更新即可实现高精度检测。
摘要：
视频异常检测（VAD）是计算机视觉中的基本挑战，尤其由于异常的开放集性质。尽管近期利用视觉语言模型（VLMs）的无训练方法显示出潜力，但通常依赖大规模、资源密集的基础模型来弥补静态提示的模糊性。我们提出QVAD，一种以问题为中心的代理框架，将VLM-LLM交互视为动态对话。通过根据视觉上下文迭代优化查询，我们的LLM代理引导较小的VLMs生成高保真描述和精确的语义推理，而无需参数更新。这种“提示更新”机制有效解锁了轻量模型的潜在能力，在UCF-Crime、XD-Violence和UBNormal数据集上实现了最先进的性能。我们进一步在单场景ComplexVAD数据集上展示了出色的泛化能力。关键的是，QVAD在高速推理和最小内存占用方面表现优异，使高级VAD能力能够在资源受限的边缘设备上部署。
英文摘要：
Video Anomaly Detection (VAD) is a fundamental challenge in computer vision, particularly due to the open-set nature of anomalies. While recent training-free approaches utilizing Vision-Language Models (VLMs) have shown promise, they typically rely on massive, resource-intensive foundation models to compensate for the ambiguity of static prompts. We argue that the bottleneck in VAD is not necessarily model capacity, but rather the static nature of inquiry. We propose QVAD, a question-centric agentic framework that treats VLM-LLM interaction as a dynamic dialogue. By iteratively refining queries based on visual context, our LLM agent guides smaller VLMs to produce high-fidelity captions and precise semantic reasoning without parameter updates. This ``prompt-updating" mechanism effectively unlocks the latent capabilities of lightweight models, enabling state-of-the-art performance on UCF-Crime, XD-Violence, and UBNormal using a fraction of the parameters required by competing methods. We further demonstrate exceptional generalizability on the single-scene ComplexVAD dataset. Crucially, QVAD achieves high inference speeds with minimal memory footprints, making advanced VAD capabilities deployable on resource-constrained edge devices.
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。
