EUVIMEDEUVIMED entdecken
Crossref

Learning Confidence-Aware Prototypes for Weakly-Supervised Video Anomaly Detection

Zhao Xie, Jinkang Luo, Kewei Wu, Zhehan Kan, Dan Guo

IEEE Transactions on Circuits and Systems for Video Technology · 2026-04 · 36 (4) · 5714-5728

DOI: 10.1109/tcsvt.2025.3628630 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-04. Verfasst von Zhao Xie und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: Natural Science Foundation of China, University Synergy Innovation Program of Anhui Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly supervised video anomaly detection aims to identify abnormal snippets in untrimmed videos. Existing methods learn prototypes to describe global representation of snippet distributions. But, in weakly-labeled videos, the normal snippets in abnormal video may take high-uncertainty labels for distribution modeling. Without confidence-aware modeling, abnormal/normal prototype distributions may overlap with each other, leading to inaccurate predictions. In this work, we propose the Unified Confident Prototype (UCP) model, which contains a feature extractor, a confidence-aware prototype learner, and a local-global prototype unifier. The prototype learning is designed to ensure proper separability, stability, and representation. First, after learning the weight of each snippet’s loss, snippets with high-uncertainty labels may take small weights. These snippets tend to lie in the overlap between abnormal/normal distributions, hindering their separation. We design uncertainty-aware sampling, which removes high-uncertainty snippets in the small-weight snippets to ensure separable prototype learning. Second, snippets with high-uncertainty labels tend to be far from the prototype center, thus falling in the low-confidence region. These snippets may enlarge the distribution’s variation, resulting in unstable prototype learning. We design confidence-aware sampling, which removes low-confidence snippets to ensure stable prototype learning. Third, after assigning pseudo labels to prototypes, we measure the prototype representation with the distribution’s purity. We design prototype distribution purification, which penalizes normal snippets in the abnormal-majority distribution with purity loss to ensure representative prototype learning. Fourth, beyond prototype learning, prototypes can be enhanced by local/global temporal semantics. We further introduce the local-global prototype unifier to learn the relations across local-global durations, thereby enhancing the semantics for anomaly detection. For weakly-supervised anomaly detection, experiments demonstrate that our method achieves state-of-the-art performance on the UCF-Crime, ShanghaiTech, and XD-Violence datasets. Moreover, to further verify the generality of our method, we further conduct experiments on THUMOS’14 for weakly-supervised temporal action localization.

Förderung

  • Natural Science Foundation of China
  • University Synergy Innovation Program of Anhui Province

Zitieren

APA

Xie, Z., Luo, J., Wu, K., Kan, Z., & Guo, D. (2026). Learning Confidence-Aware Prototypes for Weakly-Supervised Video Anomaly Detection. IEEE Transactions on Circuits and Systems for Video Technology, 36(4), 5714-5728. https://doi.org/10.1109/tcsvt.2025.3628630

Vancouver

Xie Z, Luo J, Wu K, Kan Z, Guo D. Learning Confidence-Aware Prototypes for Weakly-Supervised Video Anomaly Detection. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(4):5714-5728. doi:10.1109/tcsvt.2025.3628630

BibTeX
@article{Xie2026,
  author = {Xie, Zhao and Luo, Jinkang and Wu, Kewei and Kan, Zhehan and Guo, Dan},
  title = {Learning Confidence-Aware Prototypes for Weakly-Supervised Video Anomaly Detection},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {4},
  pages = {5714--5728},
  doi = {10.1109/tcsvt.2025.3628630}
}
Kostenlos starten →