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 25, 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

Feature selection in supervised saliency prediction.

Ming Liang, Xiaolin Hu

    IEEE Transactions on Cybernetics
    |August 15, 2014
    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

    Comment on "TECAR Therapy in Pelvic Floor Rehabilitation for Women with Pelvic Pain: A Case-Control Study".

    International urogynecology journal·2026
    Same author

    Comparison of Child-Pugh and MELD scores in predicting survival of hepatocellular carcinoma patients with splenomegaly undergoing TACE: a real-world study.

    Frontiers in medicine·2026
    Same author

    Combined Lingzhi Huang capsules and Zeng Jian health tonic accelerates skin wound healing via BMP5-mediated inhibition of ferroptosis.

    Frontiers in immunology·2026
    Same author

    Water Level Regulation Regime Shifts Drive Divergent Foraging Habitat Use by Wintering Hooded Cranes (<i>Grus monacha</i>) in Shallow Gate-controlled Lakes of the Yangtze Floodplain.

    Ecology and evolution·2026
    Same author

    Dynamic Ion-Adsorption Interface for Uniform Lithium-Ion Transport in High-Performance Lithium Metal Batteries.

    Small (Weinheim an der Bergstrasse, Germany)·2026
    Same author

    A distinct IgM immunoblot signature differentiates neurosyphilis from latent syphilis.

    Microbiology spectrum·2026
    Same journal

    An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models.

    IEEE transactions on cybernetics·2026
    Same journal

    A Quantum Self-Attention Neural Network Model on Quantum Circuits.

    IEEE transactions on cybernetics·2026
    Same journal

    Semi-Explicit Solution of Some Discrete-Time Higher-Order-Cost Mean-Field-Type Control.

    IEEE transactions on cybernetics·2026
    Same journal

    A Novel One-Step Small Object Detector for Autonomous Aerial Vehicles.

    IEEE transactions on cybernetics·2026
    Same journal

    Online Data-Driven-Based Optimal Output Tracking Control Without Initial Stabilizing Policy.

    IEEE transactions on cybernetics·2026
    Same journal

    Digital Redesign-Based Interval State Estimation for Continuous Systems With Aperiodic Discrete Measurements.

    IEEE transactions on cybernetics·2026
    See all related articles

    Researchers found that a small set of features effectively predicts human eye fixations, outperforming models using extensive feature sets. This discovery simplifies visual saliency models and enhances their efficiency.

    Area of Science:

    • Computer Vision
    • Computational Neuroscience
    • Machine Learning

    Background:

    • Models predicting visual saliency from image features often use large feature sets.
    • This approach increases computational cost and obscures which features are most effective.
    • Existing models struggle to identify the core factors driving human visual attention.

    Purpose of the Study:

    • To identify a minimal, effective set of features for predicting human eye fixations.
    • To evaluate the redundancy of features in current saliency models.
    • To assess the robustness of selected features and models across datasets and tasks.

    Main Methods:

    • Supervised feature selection was applied to identify key features for saliency prediction.
    • Models were trained and evaluated on three benchmark datasets for eye fixation prediction.

    Related Experiment Videos

    Last Updated: Apr 25, 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
  • Feature and model robustness was tested across datasets and for salient object detection.

    • Main Results:

    • A small subset of features proved sufficient for predicting human eye fixations accurately.
    • The reduced feature set achieved performance comparable to using all features.
    • The selected features and models demonstrated robustness across different datasets and tasks.

    Conclusions:

    • Visual saliency can be effectively modeled using a significantly reduced set of features.
    • Feature selection simplifies saliency models, improving efficiency without sacrificing performance.
    • The identified features are robust and generalize well across diverse datasets and visual tasks.