Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Exploring Diffusion Models for Unsupervised Video Anomaly Detection (2304.05841v2)

Published 12 Apr 2023 in cs.CV

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. “Review on deep learning approaches for anomaly event detection in video surveillance,” Electronics, vol. 12, no. 1, pp. 29, 2022.
  2. “Real-world anomaly detection in surveillance videos,” in CVPR, 2018, pp. 6479–6488.
  3. “Future frame prediction for anomaly detection – a new baseline,” in Proc. CVPR, 2018.
  4. “Anomaly detection: A survey,” ACM CSUR, vol. 41, no. 3, pp. 1–58, 2009.
  5. “Image/video deep anomaly detection: A survey,” arXiv preprint arXiv:2103.01739, 2021.
  6. “Detecting abnormal fish trajectories using clustered and labeled data,” in ICIP, 2013, pp. 1476–1480.
  7. “Deep video anomaly detection: Opportunities and challenges,” in ICDM workshops, 2021, pp. 959–966.
  8. “Abnormal event detection in videos using generative adversarial nets,” in ICIP, 2017, pp. 1577–1581.
  9. “Deep-cascade: Cascading 3d deep neural networks for fast anomaly detection and localization in crowded scenes,” IEEE TIP, vol. 26, no. 4, pp. 1992–2004, 2017.
  10. “Old is gold: Redefining the adversarially learned one-class classifier training paradigm,” in CVPR, 2020, pp. 14183–14193.
  11. “Dam: Dissimilarity attention module for weakly-supervised video anomaly detection,” in AVSS, 2021, pp. 1–8.
  12. “Weakly-supervised video anomaly detection with robust temporal feature magnitude learning,” in ICCV, 2021, pp. 4975–4986.
  13. “Generative cooperative learning for unsupervised video anomaly detection,” in CVPR, 2022, pp. 14744–14754.
  14. “Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection,” in CVPR, 2019, pp. 1705–1714.
  15. “Learning memory-guided normality for anomaly detection,” in CVPR, 2020, pp. 14372–14381.
  16. “Stabilizing adversarially learned one-class novelty detection using pseudo anomalies,” IEEE TIP, vol. 31, pp. 5963–5975, 2022.
  17. “Unsupervised anomaly detection from time-of-flight depth images,” in CVPR workshops, June 2022, pp. 231–240.
  18. “Unsupervised video anomaly detection based on sparse reconstruction,” in BDCPS. Springer, 2021, pp. 994–1001.
  19. “Elucidating the design space of diffusion-based generative models,” in NeurIPS, 2022.
  20. “Semi-orthogonal embedding for efficient unsupervised anomaly segmentation,” arXiv preprint:2105.14737, 2021.
  21. “Learning a distance function with a siamese network to localize anomalies in videos,” in WACV, 2020, pp. 2598–2607.
  22. “Joint detection and recounting of abnormal events by learning deep generic knowledge,” in ICCV, 2017, pp. 3619–3627.
  23. “Deep unsupervised learning using nonequilibrium thermodynamics,” in ICML, 2015, pp. 2256–2265.
  24. “Denoising diffusion probabilistic models,” NeurIPS, vol. 33, pp. 6840–6851, 2020.
  25. “Photorealistic text-to-image diffusion models with deep language understanding,” arXiv preprint arXiv:2205.11487, 2022.
  26. “Sdedit: Guided image synthesis and editing with stochastic differential equations,” in ICLR, 2021.
  27. “Multi-instrument music synthesis with spectrogram diffusion,” arXiv preprint arXiv:2206.05408, 2022.
  28. “Diffusiondet: Diffusion model for object detection,” arXiv preprint:2211.09788, 2022.
  29. “Diffusioninst: Diffusion model for instance segmentation,” arXiv preprint:2212.02773, 2022.
  30. “Diffusion models for medical anomaly detection,” in MICCAI. Springer, 2022, pp. 35–45.
  31. “Estimation of non-normalized statistical models by score matching.,” JMLR, vol. 6, no. 4, 2005.
  32. Ting Chen, “On the importance of noise scheduling for diffusion models,” arXiv preprint arXiv:2301.10972, 2023.
  33. “Diffusion probabilistic models for 3d point cloud generation,” in Proc. CVPR, 2021, pp. 2837–2845.
  34. “Film: Visual reasoning with a general conditioning layer,” in Proc. AAAI, 2018, vol. 32.
Citations (27)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now