GlanceVAD: Exploring Glance Supervision for Label-efficient Video Anomaly Detection

arXiv:2403.06154v1 Announce Type: new
Abstract: In recent years, video anomaly detection has been extensively investigated in both unsupervised and weakly supervised settings to alleviate costly temporal labeling. Despite significant progress, these methods still suffer from unsatisfactory results such as numerous false alarms, primarily due to the absence of precise temporal anomaly annotation. In this paper, we present a novel labeling paradigm, termed "glance annotation", to achieve a better balance between anomaly detection accuracy and annotation cost. Specifically, glance annotation is …

anomaly anomaly detection arxiv cs.cv detection glance supervision type video