arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2404.01014cs.CV
收藏

利用大型语言模型实现免训练的视频异常检测

Harnessing Large Language Models for Training-free Video Anomaly Detection

University of Trento(特伦托大学);Fondazione Bruno Kessler(布鲁诺·凯塞勒基金会)

Luca Zanella, Willi Menapace, Massimiliano Mancini, Yiming Wang, Elisa Ricci

AI总结:

本文提出免训练的LAVAD方法,利用预训练大语言模型和视觉-语言模型,通过帧级字幕生成、提示机制与跨模态相似性细化实现视频异常检测,在UCF-Crime和XD-Violence上超越无监督与单类方法。

摘要:

视频异常检测(VAD)旨在从时间上定位视频中的异常事件。现有工作大多依赖训练深度模型,在视频级监督、单类监督或无监督设置下学习正常性的分布。基于训练的方法往往具有领域特异性,因此在实际部署中成本高昂,因为任何领域变化都会涉及数据收集和模型训练。在本文中,我们彻底脱离以往的研究思路,提出基于语言的VAD(LAVAD),这是一种以新颖的免训练范式处理VAD的方法,利用预训练大型语言模型(LLMs)和现有视觉-语言模型(VLMs)的能力。我们利用基于VLM的字幕生成模型为任意测试视频的每一帧生成文本描述。借助文本场景描述,我们进一步设计了一种提示机制,以释放LLMs在时间聚合和异常分数估计方面的能力,将LLMs转变为有效的视频异常检测器。我们进一步利用模态对齐的VLMs,并提出基于跨模态相似性的有效技术,用于清理噪声字幕并细化基于LLM的异常分数。我们在两个包含真实世界监控场景的大型数据集(UCF-Crime和XD-Violence)上评估LAVAD,结果表明它在不需要任何训练或数据收集的情况下,优于无监督方法和单类方法。

英文摘要:

Video anomaly detection (VAD) aims to temporally locate abnormal events in a video. Existing works mostly rely on training deep models to learn the distribution of normality with either video-level supervision, one-class supervision, or in an unsupervised setting. Training-based methods are prone to be domain-specific, thus being costly for practical deployment as any domain change will involve data collection and model training. In this paper, we radically depart from previous efforts and propose LAnguage-based VAD (LAVAD), a method tackling VAD in a novel, training-free paradigm, exploiting the capabilities of pre-trained large language models (LLMs) and existing vision-language models (VLMs). We leverage VLM-based captioning models to generate textual descriptions for each frame of any test video. With the textual scene description, we then devise a prompting mechanism to unlock the capability of LLMs in terms of temporal aggregation and anomaly score estimation, turning LLMs into an effective video anomaly detector. We further leverage modality-aligned VLMs and propose effective techniques based on cross-modal similarity for cleaning noisy captions and refining the LLM-based anomaly scores. We evaluate LAVAD on two large datasets featuring real-world surveillance scenarios (UCF-Crime and XD-Violence), showing that it outperforms both unsupervised and one-class methods without requiring any training or data collection.

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。

↑