Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection

arXiv:2403.12172v1 Announce Type: new
Abstract: Skeleton-based video anomaly detection (SVAD) is a crucial task in computer vision. Accurately identifying abnormal patterns or events enables operators to promptly detect suspicious activities, thereby enhancing safety. Achieving this demands a comprehensive understanding of human motions, both at body and region levels, while also accounting for the wide variations of performing a single action. However, existing studies fail to simultaneously address these crucial properties. This paper introduces a novel, practical and lightweight framework, namely …

abstract accounting anomaly anomaly detection arxiv computer computer vision cs.ai cs.cv detection diffusion diffusion model events graph human jigsaw operators patterns safety type understanding video vision