无需训练，用户自定义异常事件即可检测视频异常。
AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM
- 用文本描述异常事件，直接通过视觉问答实现零样本检测。
- 在UBnormal和UCF-Crime上达顶尖性能，跨数据集泛化能力强。
- 适合无机器学习背景的用户快速部署视频异常监测系统。
视频异常检测（VAD）在计算机视觉中对视频分析与监控至关重要。然而现有模型依赖预设正常模式，难以适应多样环境，导致用户需重新训练模型或开发新AI系统，需具备机器学习知识、高性能硬件及大量数据，限制了实际应用。为此，本文提出可定制视频异常检测（C-VAD）技术及AnyAnomaly模型。C-VAD将用户定义的文本视为异常事件，检测视频中是否包含该事件。我们通过上下文感知的视觉问答，在不微调大视觉语言模型的前提下实现高效检测。为验证效果，构建了C-VAD数据集，并展示AnyAnomaly的优越性。此外，该方法在多个标准基准上表现优异，在UBnormal和UCF-Crime上达到当前最优水平，且在所有数据集上均展现出强泛化能力。代码已开源：github.com/SkiddieAhn/Paper-AnyAnomaly。
原文摘要 · Abstract (English)
Video anomaly detection (VAD) is crucial for video analysis and surveillance in computer vision. However, existing VAD models rely on learned normal patterns, which makes them difficult to apply to diverse environments. Consequently, users should retrain models or develop separate AI models for new environments, which requires expertise in machine learning, high-performance hardware, and extensive data collection, limiting the practical usability of VAD. To address these challenges, this study proposes customizable video anomaly detection (C-VAD) technique and the AnyAnomaly model. C-VAD considers user-defined text as an abnormal event and detects frames containing a specified event in a video. We effectively implemented AnyAnomaly using a context-aware visual question answering without fine-tuning the large vision language model. To validate the effectiveness of the proposed model, we constructed C-VAD datasets and demonstrated the superiority of AnyAnomaly. Furthermore, our approach showed competitive results on VAD benchmarks, achieving state-of-the-art performance on UBnormal and UCF-Crime and surpassing other methods in generalization across all datasets. Our code is available online at github.com/SkiddieAhn/Paper-AnyAnomaly.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。