MULDE: Multiscale Log-Density Estimation via Denoising Score Matching for Video Anomaly Detection

arXiv:2403.14497v1 Announce Type: new
Abstract: We propose a novel approach to video anomaly detection: we treat feature vectors extracted from videos as realizations of a random variable with a fixed distribution and model this distribution with a neural network. This lets us estimate the likelihood of test videos and detect video anomalies by thresholding the likelihood estimates. We train our video anomaly detector using a modification of denoising score matching, a method that injects training data with noise to facilitate …

abstract anomaly anomaly detection arxiv cs.cv denoising detection distribution feature likelihood network neural network novel random test type vectors via video videos