Patch Spatio-Temporal Relation Prediction for Video Anomaly Detection

arXiv:2403.19111v1 Announce Type: new
Abstract: Video Anomaly Detection (VAD), aiming to identify abnormalities within a specific context and timeframe, is crucial for intelligent Video Surveillance Systems. While recent deep learning-based VAD models have shown promising results by generating high-resolution frames, they often lack competence in preserving detailed spatial and temporal coherence in video frames. To tackle this issue, we propose a self-supervised learning approach for VAD through an inter-patch relationship prediction task. Specifically, we introduce a two-branch vision transformer network …

abstract anomaly anomaly detection arxiv context cs.cv deep learning detection identify intelligent prediction resolution results spatial surveillance systems temporal type video video surveillance