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 30, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.3K

FTGID: Fine-Grained Text-Driven Framework for Universal Generative Image Detection.

Zhipeng Huang, Liqun Lin, Bolin Chen

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |April 28, 2026
    PubMed
    Summary
    This summary is machine-generated.

    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

    Gamabufotalin suppresses pancreatic cancer through redox-homeostasis disruption by G6PD downregulation.

    Journal of translational medicine·2026
    Same author

    Squalene in <i>Camellia oleifera</i>: Biosynthetic Pathways, Regulatory Networks, and Functional Perspectives.

    Plants (Basel, Switzerland)·2026
    Same author

    A multicenter, clinically interpretable prediction model for malignancy risk in C-TIRADS 3-4 thyroid nodules.

    Frontiers in oncology·2026
    Same author

    Sacituzumab tirumotecan plus pembrolizumab versus pembrolizumab in PD-L1-positive advanced non-small-cell lung cancer (OptiTROP-Lung05): interim analysis of a randomised, open-label, phase 3 trial.

    Lancet (London, England)·2026
    Same author

    CGHNet: Cross-Guided 2D-3D Hybrid Network with attention mechanism for focal liver lesion classification.

    Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2026
    Same author

    Multimodal Image Representation Learning With Limited Visual-Tactile Data.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    GoP-based Quality Enhancement on Video Compression.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces a Fine-grained Text-driven Generative Image Detection (FTGID) framework to improve the detection of realistic AI-generated forgeries. FTGID enhances robustness and interpretability by using multi-modal cues for more reliable generative image detection.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Generative models create realistic forgeries, posing security challenges.
    • Current detection methods lack generalization and rely on coarse prompts.
    • Vision-Language Model (VLM)-based methods have limitations in cross-modal alignment.

    Purpose of the Study:

    • To propose a Fine-grained Text-driven Generative Image Detection (FTGID) framework.
    • To enable comprehensive detection of generative images using multi-modal cues.
    • To enhance the robustness and interpretability of generative image detection.

    Main Methods:

    • Layer-wise Adaptive Global Extractor (LAGE) for multi-level representation stabilization.
    • Fine-grained Text-guided Local Enhancer (FTLE) for patch-level text-visual interaction.

    Related Experiment Videos

    Last Updated: Apr 30, 2026

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    1.3K
  • High-frequency Artifact Feature Extractor (HAFE) for capturing subtle generative artifacts.

    • Main Results:

    • FTGID consistently outperforms state-of-the-art Generative Image Detection (GID) methods.
    • Achieves superior performance across diverse generative models and unseen datasets.
    • Demonstrates enhanced robustness and interpretability in open-world scenarios.

    Conclusions:

    • The proposed FTGID framework offers a significant advancement in detecting AI-generated images.
    • FTGID provides a more reliable and interpretable solution for generative image detection.
    • The framework shows strong generalization capabilities on diverse and novel datasets.