Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Apr 14, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.7K

TrCLIP-VAD : Weak supervised video anomaly detection by improving CLIP training with text rewriting.

Shengjie Shen1, Ziteng Guo1, Yahui Li1

  • 1School of Computer Science and Technology, Xinjiang University, Urumqi, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 12, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Discovery, synthesis, and acaricidal activity evaluation of deep learning-assisted diphenyloxazoline thiosulfonate derivatives.

Pest management science·2026
Same author

Hybrid movement strategies in orthopedic oncology: Mechanistic integration of musculoskeletal and tumor-host interactions.

Seminars in oncology·2026
Same author

Ligand-stabilized dilithium (C6F5)2Li2 featuring two planar tetracoordinate lithium and carbon centers.

The Journal of chemical physics·2026
Same author

Quadruple Bonding of Alkaline Earth Atoms in AeCLi<sub>4</sub> (Ae = Be - Ba) Complexes.

Journal of computational chemistry·2026
Same author

Light-Written Nonvolatile Polarization via Defect-Engineered Charge Trapping.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Exercise-responsive Wnt/β-catenin signaling across metabolic tissues during aging: A narrative review.

Archives of gerontology and geriatrics·2026
This summary is machine-generated.

This study introduces TrCLIP-VAD, a novel text rewriting approach for video anomaly detection (VAD). It enhances semantic understanding by rewriting video captions, significantly improving VAD performance on benchmark datasets.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Existing contrastive language-image pre-training (CLIP) based video anomaly detection (VAD) methods often neglect high-level semantic information like textual descriptions of abnormal events.
  • Current VAD techniques commonly augment video frames but fail to vary text inputs, limiting semantic diversity during training.

Purpose of the Study:

  • To propose TrCLIP-VAD, a novel CLIP-based VAD model that leverages text rewriting to improve the detection of anomalies.
  • To enhance the semantic representation of videos by rewriting existing captions using large language models (LLMs).

Main Methods:

  • Developed TrCLIP-VAD, a model that generates source captions for videos and rewrites them using In-Context Learning (ICL) from LLMs.
  • Integrated a Local-Global Multi-scale Mamba (LGM-Mamba) module to capture temporal dependencies and fuse visual and textual features.
Keywords:
CLIPContrastive learningMambaText rewritingVideo anomaly detection

Related Experiment Videos

Last Updated: Apr 14, 2026

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.7K
  • Fused rewritten captions with visual features for anomaly detection.

    • Main Results:

    • TrCLIP-VAD achieved state-of-the-art performance on the XD-Violence and UCF-Crime datasets.
    • Achieved 86.05% Average Precision (AP) on the XD-Violence dataset.
    • Achieved 88.59% Area Under the Curve (AUC) on the UCF-Crime dataset.

    Conclusions:

    • The proposed text rewriting strategy significantly enhances semantic expression for VAD.
    • The LGM-Mamba module effectively captures temporal dynamics and deepens feature fusion, boosting detection accuracy.
    • TrCLIP-VAD represents a significant advancement in video anomaly detection by integrating advanced LLM and Mamba-based techniques.