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 28, 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

Relative saliency model over multiple images with an application to yarn surface evaluation.

Zhen Liang, Bingang Xu, Zheru Chi

    IEEE Transactions on Cybernetics
    |June 12, 2014
    PubMed
    Summary

    This study introduces relative saliency, a new visual attention model for comparing multiple images. It enables objective evaluation of visual importance across image sets, demonstrated effectively in yarn surface inspection.

    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

    Unveiling the synergy of Interface and defects in V<sub>2</sub>O<sub>3</sub>/VN heterojunctions for high-performance aqueous zinc-ion batteries.

    Journal of colloid and interface science·2026
    Same author

    Steric Coordination Modulated Iodine Chemistry With Four-Electron Conversion for Zinc-Iodine Batteries.

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

    Double-Sided Mechanical Interlocking Enables Soft-Rigid Conductive Interfaces With a Record High Toughness for Flexible Electronics.

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

    A Folded, Structure-Integrated Bimodal Sensor Enabling Non-Contact and Tactile Perception for Intelligent Robots.

    Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
    Same author

    Oxygen-Synergized All-Fiber Hydrovoltaics With Milliamp Output Toward Self-Powered Breathable Electronics.

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

    Bioinspired Dual-Scale Crack Manipulation Enabling 325%-Stretchable Metal Film Conductors for AI-Empowered Electronic Skins.

    Nano-micro letters·2026

    Area of Science:

    • Computer Vision
    • Image Understanding
    • Visual Attention Modeling

    Background:

    • Existing saliency models evaluate "absolute saliency" within single images, limiting cross-image comparisons.
    • Tasks like visual inspection require comparing saliency across multiple images, a capability lacking in current models.

    Purpose of the Study:

    • To explore visual attention models for multi-image comparison.
    • To propose a novel "relative saliency" model for evaluating visual importance across a set of images.

    Main Methods:

    • Developed a relative saliency model combining bottom-up and top-down attention mechanisms.
    • Proposed a structural feature extraction strategy with two levels (high, low) and three types (global, local-local, local-global).
    • Constructed mapping functions to translate extracted features into relative saliency values.

    More Related Videos

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.6K

    Related Experiment Videos

    Last Updated: Apr 28, 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
    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    3.6K

    Main Results:

    • The proposed model enables relative saliency evaluation for multi-image content.
    • Demonstrated the model's effectiveness in a yarn surface evaluation task.
    • Validated the concept of relative saliency using eye-tracking data.

    Conclusions:

    • Relative saliency offers a comparable measure of visual importance across multiple images.
    • The developed model provides a robust framework for multi-image visual inspection tasks.
    • Further research can extend this approach to diverse comparative visual analysis applications.