Video anomaly detection (VAD) is a significant computer vision problem. Existing deep
neural network (DNN) based VAD methods mostly follow the route of frame reconstruction or …

Anomaly detection is commonly pursued as a one-class classification problem, where
models can only learn from normal training samples, while being evaluated on both normal …

Weakly supervised detection of anomalies in surveillance videos is a challenging task.
Going beyond existing works that have deficient capabilities to localize anomalies in long …

Increasing scene-awareness is a key challenge in video anomaly detection (VAD). In this
work, we propose a hierarchical semantic contrast (HSC) method to learn a scene-aware …

Video anomaly detection (VAD) aims at localizing unexpected actions or activities in a video
sequence. Existing mainstream VAD techniques are based on either the one-class …

Anomaly detection in video is a challenging computer vision problem. Due to the lack of
anomalous events at training time, anomaly detection requires the design of learning …

Detecting abnormal events in video is commonly framed as a one-class classification task,
where training videos contain only normal events, while test videos encompass both normal …

Weakly supervised video anomaly detection aims to identify abnormal events in videos
using only video-level labels. Recently, two-stage self-training methods have achieved …

Anomaly detection in the video is an important research area and a challenging task in real
applications. Due to the unavailability of large-scale annotated anomaly events, most …

Abstract Video Anomaly Detection (VAD) is an important topic in computer vision. Motivated
by the recent advances in self-supervised learning, this paper addresses VAD by solving an …