Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection

arXiv:2403.01169v1 Announce Type: new
Abstract: Most models for weakly supervised video anomaly detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly. The ambiguous nature of anomaly definitions across contexts introduces bias in detecting abnormal and normal snippets within the abnormal bag. Taking the first step to show the model why it is anomalous, a novel framework is proposed to guide the learning of suspected anomalies from event prompts. Given …

abstract anomaly anomaly detection arxiv bias cs.cv definitions detection event instance learn multiple nature normal prompts type video