Harnessing Large Language Models for Training-free Video Anomaly Detection

arXiv:2404.01014v1 Announce Type: new
Abstract: 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 …

abstract anomaly anomaly detection arxiv class cs.cv detection distribution domain events free language language models large language large language models learn normality supervision training type unsupervised video