Papers › Video Anomaly Detection by Estimating Likelihood of Representations

Video Anomaly Detection by Estimating Likelihood of Representations

2 Dec 2020arXiv:2012.01468archive 2025-07-28

Yuqi Ouyang, Victor Sanchez

Video anomaly detection is a challenging task not only because it involves solving many sub-tasks such as motion representation, object localization and action recognition, but also because it is commonly considered as an unsupervised learning problem that involves detecting outliers. Traditionally, solutions to this task have focused on the mapping between video frames and their low-dimensional features, while ignoring the spatial connections of those features. Recent solutions focus on analyzing these spatial connections by using hard clustering techniques, such as K-Means, or applying neural networks to map latent features to a general understanding, such as action attributes. In order to solve video anomaly in the latent feature space, we propose a deep probabilistic model to transfer this task into a density estimation problem where latent manifolds are generated by a deep denoising autoencoder and clustered by expectation maximization. Evaluations on several benchmarks datasets show the strengths of our model, achieving outstanding performance on challenging datasets.

PaperPDFCode

Code

wufan-tb/gmm_dae mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionAnomaly DetectionClusteringDensity EstimationObject LocalizationVideo Anomaly Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Denoising Autoencoder

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections