Aligning Normal Representations in Diffusion Model for Video Anomaly Detection
IEEE Transactions on Circuits and Systems for Video Technology · 2026-02 · 36 (2) · 2083-2094
DOI: 10.1109/tcsvt.2025.3602841 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-02. Verfasst von Chongye Guo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Eastern Talent Plan Leading Project.
Abstract (Originalsprache)
Recent advances have highlighted the potential of diffusion models in Video Anomaly Detection (VAD). Diffusion models are typically employed to generate negative instances to distinguish them from positive ones. However, the existing diffusion model architectures, generally based on the reconstruction of low-level noisy features, introduce spurious correlations due to shortcut learning, which undermines the robustness of anomaly detection. In this work, we leverage normal-specific representations to guide behavior restoration by aligning disentangled task-relevant representations within the diffusion model. we propose a normal representation-guided conditional diffusion model for unsupervised VAD by aligning normal-specific representations. Inspired by prior knowledge of anomaly discrimination, we decompose normal behavior features into normal-specific and VAD-irrelevant representations into independent channels based on contrastive learning. We introduce a group-supervised learning strategy in learning patch-wise generation guided by normal-specific representations. A gradient-based representation alignment loss enforces the alignment between normal semantics and the target patches. This process enables the diffusion model to understand normal patterns for anomaly detection. Extensive experimental results conducted on VAD benchmarks demonstrate the effectiveness of our methods.
Förderung
- Eastern Talent Plan Leading Project
Zitieren
APA
Guo, C., Li, L., Ren, Y., Zhang, X., & Feng, G. (2026). Aligning Normal Representations in Diffusion Model for Video Anomaly Detection. IEEE Transactions on Circuits and Systems for Video Technology, 36(2), 2083-2094. https://doi.org/10.1109/tcsvt.2025.3602841
Vancouver
Guo C, Li L, Ren Y, Zhang X, Feng G. Aligning Normal Representations in Diffusion Model for Video Anomaly Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(2):2083-2094. doi:10.1109/tcsvt.2025.3602841
BibTeX
@article{Guo2026,
author = {Guo, Chongye and Li, Li and Ren, Yanli and Zhang, Xinpeng and Feng, Guorui},
title = {Aligning Normal Representations in Diffusion Model for Video Anomaly Detection},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {2},
pages = {2083--2094},
doi = {10.1109/tcsvt.2025.3602841}
}
EUVIMED