mlsanityData to 13 Oct 2026

Exploring Diffusion Models for Unsupervised Video Anomaly Detection

arXiv 2304.05841 ↗First posted 12 Apr 2023cs.CVcited by 23

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

This paper investigates the performance of diffusion models for video anomaly detection (VAD) within the most challenging but also the most operational scenario in which the data annotations are not used. As being sparse, diverse, contextual, and often ambiguous, detecting abnormal events precisely is a very ambitious task. To this end, we rely only on the information-rich spatio-temporal data, and the reconstruction power of the diffusion models such that a high reconstruction error is utilized to decide the abnormality. Experiments performed on two large-scale video anomaly detection datasets demonstrate the consistent improvement of the proposed method over the state-of-the-art generative models while in some cases our method achieves better scores than the more complex models. This is the first study using a diffusion model and examining its parameters' influence to present guidance for VAD in surveillance scenarios.

Key facts. Cited by 23 papers in the map (data through 13 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 27 of its 34 references that are in the map. First posted on arXiv 12 Apr 2023.

Builds on

27 of 34 references.

References · 27

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,952
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,023
  3. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,339
  4. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,023
  5. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,306
  6. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,921
  7. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  8. 2018Real-world Anomaly Detection in Surveillance Videoscited by 573
  9. 2019Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detectioncited by 562
  10. 2017Future Frame Prediction for Anomaly Detection -- A New Baselinecited by 391
  11. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  12. 2020Learning Memory-guided Normality for Anomaly Detectioncited by 278
15 more
  1. 2022Diffusion Models for Medical Anomaly Detectioncited by 232
  2. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 228
  3. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 193
  4. 2020Old is Gold: Redefining the Adversarially Learned One-Class Classifier Training Paradigmcited by 115
  5. 2022Generative Cooperative Learning for Unsupervised Video Anomaly Detectioncited by 102
  6. 2017Abnormal Event Detection in Videos using Generative Adversarial Netscited by 82
  7. 2017Joint Detection and Recounting of Abnormal Events by Learning Deep Generic Knowledgecited by 55
  8. 2022DiffusionInst: Diffusion Model for Instance Segmentationcited by 49
  9. 2022Multi-instrument Music Synthesis with Spectrogram Diffusioncited by 42
  10. 2020Learning a distance function with a Siamese network to localize anomalies in videoscited by 31
  11. 2021Semi-orthogonal Embedding for Efficient Unsupervised Anomaly Segmentationcited by 26
  12. 2021Deep Video Anomaly Detection: Opportunities and Challengescited by 14
  13. 2022Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomaliescited by 14
  14. 2021Image/Video Deep Anomaly Detection: A Surveycited by 10
  15. 2022Unsupervised Anomaly Detection from Time-of-Flight Depth Imagescited by 6

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2023: 8; 2024: 9; 2025: 4; 2026: 2.

23 papers.

Sort:

By area:

  1. 2023A Survey on Video Diffusion Modelscited by 206
  2. 2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 125
  3. 2024Harnessing Large Language Models for Training-free Video Anomaly Detectioncited by 85
  4. 2024Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularitycited by 68
  5. 2024Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLMcited by 64
  6. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 60
  7. 2023Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectorscited by 37
  8. 2024Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentationcited by 27
  9. 2024Video Anomaly Detection in 10 Years: A Survey and Outlookcited by 18
  10. 2025A Survey on Diffusion Models for Anomaly Detectioncited by 13
  11. 2025Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detectioncited by 12
  12. 2023Survey on video anomaly detection in dynamic scenes with moving camerascited by 10
11 more
  1. 2023Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approachcited by 10
  2. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  3. 2024Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detectioncited by 6
  4. 2023TabADM: Unsupervised Tabular Anomaly Detection with Diffusion Modelscited by 5
  5. 2024Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detectioncited by 5
  6. 2023DiffusionVMR: Diffusion Model for Joint Video Moment Retrieval and Highlight Detectioncited by 2
  7. 2023Diffusion-Based Particle-DETR for BEV Perceptioncited by 2
  8. 2025TRACES: Temporal Recall with Contextual Embeddings for Real-Time Video Anomaly Detectioncited by 1
  9. 2024Exploring Out-of-distribution Detection for Sparse-view Computed Tomography with Diffusion Modelscited by 0
  10. 2026Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detectioncited by 0
  11. 2026Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understandingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Unsupervised Video Anomaly Detection with Diffusion Models Conditioned on Compact Motion Representations
  2. 2024Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model
  3. 2025Research on Anomaly Detection Methods Based on Diffusion Models
  4. 2024Anomaly detection using Diffusion-based methods
  5. 2024GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection
  6. 2025Single-Step Reconstruction-Free Anomaly Detection and Segmentation via Diffusion Models
  7. 2023On Diffusion Modeling for Anomaly Detection
  8. 2024Dynamic Addition of Noise in a Diffusion Model for Anomaly Detection