EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Short-Long Temporal Normality Deviation for Weakly Supervised Video Anomaly Detection

Huiting Wei, Zihong Guo, Kaibei Li, Jie Zou

Big Data and Cognitive Computing · 04.11.2026 · 10 (11) · 377

DOI: 10.3390/bdcc10110377 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 04.11.2026. Verfasst von Huiting Wei und 3 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sichuan Science and Technology Program, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly supervised video anomaly detection (WSVAD) tries to find abnormal events in untrimmed videos, while only video-level labels are given. However, many existing methods still have two main problems. First, abnormal events may last for different lengths of time, and their temporal changes are also not always the same; therefore, it is hard for one single time scale to collect enough useful anomaly information. Second, most current methods select abnormal segments mainly according to high anomaly scores, but these scores may be influenced by obvious visual regions, background changes, or scene-related bias, so the final anomaly localization may become unstable. To deal with these problems, this paper proposes STND-VAD, a short-long temporal normality-deviation framework for WSVAD. In this framework, a multi-scale dilated temporal feature enhancement module is first used to obtain contextual information from different temporal ranges. Then, this paper builds short-term and long-term MLP discriminative branches, so that local instant changes and longer temporal changes can be modeled separately. Besides, a normality-deviation evidence calibration mechanism is designed, which learns normal prototypes and measures how much each segment deviates from these normal patterns; in this way, it provides extra constraints for anomaly responses and reduces the influence of unreliable high-response segments. Experiments on three public benchmark datasets show that STND-VAD is effective and can achieve competitive anomaly detection results.

Förderung

  • Sichuan Science and Technology Program
  • National Natural Science Foundation of China

Zitieren

APA

Wei, H., Guo, Z., Li, K., & Zou, J. (2026). Short-Long Temporal Normality Deviation for Weakly Supervised Video Anomaly Detection. Big Data and Cognitive Computing, 10(11), 377. https://doi.org/10.3390/bdcc10110377

Vancouver

Wei H, Guo Z, Li K, Zou J. Short-Long Temporal Normality Deviation for Weakly Supervised Video Anomaly Detection. Big Data and Cognitive Computing. 2026;10(11):377. doi:10.3390/bdcc10110377

BibTeX
@article{Wei2026,
  author = {Wei, Huiting and Guo, Zihong and Li, Kaibei and Zou, Jie},
  title = {Short-Long Temporal Normality Deviation for Weakly Supervised Video Anomaly Detection},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {11},
  pages = {377},
  doi = {10.3390/bdcc10110377}
}
Kostenlos starten →