[ICIAP 2023] Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations
Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations
Anil Osman Tur, Nicola Dall'Asen, Cigdem Beyan, Elisa Ricci
University of Trento, Fondazione Bruno Kessler, Trento, Italy,
Please follow the instructions in INSTALL.md.
Please follow the instructions in DATASET.md for data preparation.
Implemented diffusion models are in the k_diffusion/models folder. The models are trained with train_ano*.py scripts.
The autoencoder model is re-implemented from the descriptions of the paper Generative Cooperative Learning for Unsupervised Video Anomaly Detection. Used for generating the baselines for the paper. Our implementation of it can be in here.
Please use the following BibTeX entry for citation.
@InProceedings{tur2023unsupervised,
author="Tur, Anil Osman and Dall'Asen, Nicola and Beyan, Cigdem and Ricci, Elisa",
editor="Foresti, Gian Luca and Fusiello, Andrea and Hancock, Edwin",
title="Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations",
booktitle="Image Analysis and Processing -- ICIAP 2023",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="49--62",
isbn="978-3-031-43153-1"
}