# Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations

arXiv: https://arxiv.org/abs/2307.01533 · HTML: https://mlsanity.com/paper/2307.01533/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 4 Jul 2023.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 21 of 21)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Diffusion Models for Medical Anomaly Detection](https://mlsanity.com/paper/2203.04306/) (2022)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [A Semi-supervised Graph Attentive Network for Financial Fraud Detection](https://mlsanity.com/paper/2003.01171/) (2020)
- [Anomaly Detection in Video Sequence with Appearance-Motion Correspondence](https://mlsanity.com/paper/1908.06351/) (2019)
- [Generative Cooperative Learning for Unsupervised Video Anomaly Detection](https://mlsanity.com/paper/2203.03962/) (2022)
- [Abnormal Event Detection in Videos using Generative Adversarial Nets](https://mlsanity.com/paper/1708.09644/) (2017)
- [Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentation](https://mlsanity.com/paper/2105.14737/) (2021)
- [Deep Video Anomaly Detection: Opportunities and Challenges](https://mlsanity.com/paper/2110.05086/) (2021)
- [Image/Video Deep Anomaly Detection: A Survey](https://mlsanity.com/paper/2103.01739/) (2021)
- [Dynamic Gesture Recognition by Using CNNs and Star RGB: a Temporal Information Condensation](https://mlsanity.com/paper/1904.08505/) (2019)
- [Ordered Pooling of Optical Flow Sequences for Action Recognition](https://mlsanity.com/paper/1701.03246/) (2017)
- [Constructing a meta-learner for unsupervised anomaly detection](https://mlsanity.com/paper/2304.11438/) (2023)

## Built on by (most cited first, 19 of 19)

- [A Survey on Video Diffusion Models](https://mlsanity.com/paper/2310.10647/) (2023)
- [Harnessing Large Language Models for Training-free Video Anomaly Detection](https://mlsanity.com/paper/2404.01014/) (2024)
- [VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models](https://mlsanity.com/paper/2412.01095/) (2024)
- [VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree](https://mlsanity.com/paper/2510.22693/) (2025)
- [A Survey on Diffusion Models for Anomaly Detection](https://mlsanity.com/paper/2501.11430/) (2025)
- [Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection](https://mlsanity.com/paper/2505.15205/) (2025)
- [MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection](https://mlsanity.com/paper/2510.21449/) (2025)
- [Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach](https://mlsanity.com/paper/2311.16514/) (2023)
- [HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs](https://mlsanity.com/paper/2507.17394/) (2025)
- [Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting](https://mlsanity.com/paper/2510.02155/) (2025)
- [Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection](https://mlsanity.com/paper/2412.03044/) (2024)
- [HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection](https://mlsanity.com/paper/2512.17601/) (2025)
- [Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection](https://mlsanity.com/paper/2602.24021/) (2026)
- [GuardReasoner-Omni: A Reasoning-based Multi-modal Guardrail for Text, Image, Video, and Audio](https://mlsanity.com/paper/2602.03328/) (2026)
- [TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning](https://mlsanity.com/paper/2608.11820/) (2026)
- [TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detection](https://mlsanity.com/paper/2511.00580/) (2025)
- [PrismVAU: Prompt-Refined Inference System for Multimodal Video Anomaly Understanding](https://mlsanity.com/paper/2601.02927/) (2026)
- [Mitral Regurgitation Recognition based on Unsupervised Out-of-Distribution Detection with Residual Diffusion Amplification](https://mlsanity.com/paper/2407.21497/) (2024)
- [Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection](https://mlsanity.com/paper/2603.13374/) (2026)

## Abstract (arXiv)

This paper aims to address the unsupervised video anomaly detection (VAD) problem, which involves classifying each frame in a video as normal or abnormal, without any access to labels. To accomplish this, the proposed method employs conditional diffusion models, where the input data is the spatiotemporal features extracted from a pre-trained network, and the condition is the features extracted from compact motion representations that summarize a given video segment in terms of its motion and appearance. Our method utilizes a data-driven threshold and considers a high reconstruction error as an indicator of anomalous events. This study is the first to utilize compact motion representations for VAD and the experiments conducted on two large-scale VAD benchmarks demonstrate that they supply relevant information to the diffusion model, and consequently improve VAD performances w.r.t the prior art. Importantly, our method exhibits better generalization performance across different datasets, notably outperforming both the state-of-the-art and baseline methods. The code of our method is available at https://github.com/AnilOsmanTur/conditioned_video_anomaly_diffusion