EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

WSVAD-CLIP: Temporally Aware and Prompt Learning with CLIP for Weakly Supervised Video Anomaly Detection

Min Li iD, Jing Sang iD, Yuanyao Lu iD, Lina Du

Journal of Imaging · 10.10.2025 · 11 (10) · 354

DOI: 10.3390/jimaging11100354 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 10.10.2025. Verfasst von Min Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence and Computer Science, North China University of Technology, No. 5 Jinyuanzhuang Road, Beijing 100144, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, North China University of Technology Research Start-up Fund Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Weakly Supervised Video Anomaly Detection (WSVAD) is a critical task in computer vision. It aims to localize and recognize abnormal behaviors using only video-level labels. Without frame-level annotations, it becomes significantly challenging to model temporal dependencies. Given the diversity of abnormal events, it is also difficult to model semantic representations. Recently, the cross-modal pre-trained model Contrastive Language-Image Pretraining (CLIP) has shown a strong ability to align visual and textual information. This provides new opportunities for video anomaly detection. Inspired by CLIP, WSVAD-CLIP is proposed as a framework that uses its cross-modal knowledge to bridge the semantic gap between text and vision. First, the Axial-Graph (AG) Module is introduced. It combines an Axial Transformer and Lite Graph Attention Networks (LiteGAT) to capture global temporal structures and local abnormal correlations. Second, a Text Prompt mechanism is designed. It fuses a learnable prompt with a knowledge-enhanced prompt to improve the semantic expressiveness of category embeddings. Third, the Abnormal Visual-Guided Text Prompt (AVGTP) mechanism is proposed to aggregate anomalous visual context for adaptively refining textual representations. Extensive experiments on UCF-Crime and XD-Violence datasets show that WSVAD-CLIP notably outperforms existing methods in coarse-grained anomaly detection. It also achieves superior performance in fine-grained anomaly recognition tasks, validating its effectiveness and generalizability.

Schlagwörter

Stichwörter der Autor:innen

Axial-Graph ModuleCLIPText Prompt MechanismVideo Anomaly DetectionWSVAD-CLIP

Autor:innen und Institutionen

  • School of Artificial Intelligence and Computer Science, North China University of Technology, No. 5 Jinyuanzhuang Road, Beijing 100144, China.

ORCID-Profile: Min Li, Jing Sang, Yuanyao Lu

Förderung

  • National Natural Science Foundation of China
  • North China University of Technology Research Start-up Fund Project

Zitieren

APA

Li, M., Sang, J., Lu, Y., & Du, L. (2025). WSVAD-CLIP: Temporally Aware and Prompt Learning with CLIP for Weakly Supervised Video Anomaly Detection. Journal of Imaging, 11(10), 354. https://doi.org/10.3390/jimaging11100354

Vancouver

Li M, Sang J, Lu Y, Du L. WSVAD-CLIP: Temporally Aware and Prompt Learning with CLIP for Weakly Supervised Video Anomaly Detection. Journal of Imaging. 2025;11(10):354. doi:10.3390/jimaging11100354

BibTeX
@article{Li2025,
  author = {Li, Min and Sang, Jing and Lu, Yuanyao and Du, Lina},
  title = {WSVAD-CLIP: Temporally Aware and Prompt Learning with CLIP for Weakly Supervised Video Anomaly Detection},
  journal = {Journal of Imaging},
  year = {2025},
  volume = {11},
  number = {10},
  pages = {354},
  doi = {10.3390/jimaging11100354}
}
Kostenlos starten →