A Survey on Self-Supervised Learning-Based Video Anomaly Detection

Video anomaly detection (VAD) exhibits promising applications across diverse domains, bolstering intelligence, security, and operational efficiency, thereby catalyzing industry growth. This paper begins by examining the research background and significance of VAD, providing an in-depth analysis of its relevance across various sectors. Subsequently, from a machine learning standpoint, recent advancements in self-supervised learning (SSL)-based VAD models are systematically categorized and summarized, elucidating their underlying principles and deployment scenarios. Additionally, commonly utilized datasets in VAD are introduced to facilitate readers' understanding of model assessment and comparative analysis. Lastly, discussions on future trajectories and extant challenges in VAD are undertaken to foster deeper exploration and propel the advancement of this domain.