Harnessing Large Language Models for Training-free Video Anomaly Detection

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zanella, Luca, Menapace, Willi, Mancini, Massimiliano, Wang, Yiming, Ricci, Elisa
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910393757073408
author Zanella, Luca
Menapace, Willi
Mancini, Massimiliano
Wang, Yiming
Ricci, Elisa
author_facet Zanella, Luca
Menapace, Willi
Mancini, Massimiliano
Wang, Yiming
Ricci, Elisa
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01014
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Harnessing Large Language Models for Training-free Video Anomaly Detection
Zanella, Luca
Menapace, Willi
Mancini, Massimiliano
Wang, Yiming
Ricci, Elisa
Computer Vision and Pattern Recognition
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.
title Harnessing Large Language Models for Training-free Video Anomaly Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.01014