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 11, 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

1.2K

Adaptive Metric Learning for Saliency Detection.

Shuang Li, Huchuan Lu, Zhe Lin

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |June 9, 2015
    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

    Aggregating global-scale pixel-wise forgery cues within a graph.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    DiMuS: Disentangled Multi-Signal Learning for Weakly Supervised Point-Based 3D Object Detection.

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

    Visual-Textual Information-Driven Tactile Data Generation Method.

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

    Class Sensitive Calibration and Discrepancy-Aware Synthesis for Semi-Supervised Medical Image Segmentation.

    IEEE journal of biomedical and health informatics·2026
    Same author

    Diffusion-based cross-staining feature transformation for whole slide image analysis: From H&E to IHC representation learning.

    Medical image analysis·2026
    Same author

    SD-ReID: View-Aware Stable Diffusion for Aerial-Ground Person Re-Identification.

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

    Style-Aware Contrastive Test-Time Adaptation: A Dual-Cache Model for Robust Vision-Language Alignment.

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

    Semantic Frame Interpolation.

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

    Physics-Guided Cross-Modal Decoupling with Test-Time Adaptation for Hyperspectral Image Restoration.

    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
    See all related articles

    We introduce an adaptive metric learning algorithm (AML) for visual saliency detection. This method uses complementary Mahalanobis distance metrics to accurately estimate superpixel saliency, outperforming current state-of-the-art approaches.

    Area of Science:

    • Computer Vision
    • Machine Learning

    Background:

    • Visual saliency detection is crucial for image understanding.
    • Existing methods often rely on low-level features and Euclidean distances.
    • A need exists for more robust and accurate saliency estimation techniques.

    Purpose of the Study:

    • To propose a novel adaptive metric learning algorithm (AML) for enhanced visual saliency detection.
    • To improve the estimation of superpixel saliency by leveraging learned distance metrics.
    • To develop a method that effectively distinguishes salient objects from the background.

    Main Methods:

    • Developed an adaptive metric learning (AML) algorithm utilizing two complementary Mahalanobis distance metrics: generic metric learning (GML) and specific metric learning (SML).
    • Employed a superpixelwise Fisher vector coding approach for improved feature representation.

    More Related Videos

    Investigating the Deployment of Visual Attention Before Accurate and Averaging Saccades via Eye Tracking and Assessment of Visual Sensitivity
    06:46

    Investigating the Deployment of Visual Attention Before Accurate and Averaging Saccades via Eye Tracking and Assessment of Visual Sensitivity

    Published on: March 18, 2019

    7.6K

    Related Experiment Videos

    Last Updated: Apr 11, 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

    1.2K
    Investigating the Deployment of Visual Attention Before Accurate and Averaging Saccades via Eye Tracking and Assessment of Visual Sensitivity
    06:46

    Investigating the Deployment of Visual Attention Before Accurate and Averaging Saccades via Eye Tracking and Assessment of Visual Sensitivity

    Published on: March 18, 2019

    7.6K
  • Integrated contextual and multiscale information with an accurate seed selection mechanism.

    • Main Results:

    • The fused GML and SML metrics effectively enhance relevant information and reduce irrelevant details.
    • The superpixelwise Fisher vector coding approach significantly improves the distinction between salient objects and background.
    • Experimental results demonstrate that the proposed AML algorithm achieves superior performance compared to state-of-the-art methods.

    Conclusions:

    • The proposed adaptive metric learning algorithm offers a significant advancement in visual saliency detection.
    • Combining global and image-specific metric learning strategies proves effective.
    • The method provides a robust framework for accurate and efficient saliency mapping.