Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach

arXiv:2311.16514v2 Announce Type: replace-cross
Abstract: Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos with normal instances while test data contains both normal and anomalous instances. Recent works have investigated the creation of pseudo-anomalies (PAs) using only the normal data and making strong assumptions about real-world anomalies with regards to abnormality of objects and speed of motion to inject prior information about anomalies …

abstract anomaly anomaly detection arxiv class classification cs.ai cs.cv cs.lg data detection instances normal recognition set temporal test training training data type via video videos