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: Dec 5, 2025

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

860

Hierarchical and Interactive Refinement Network for Edge-Preserving Salient Object Detection.

Sanping Zhou, Jinjun Wang, Le Wang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |October 14, 2020
    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

    Pyramid contrastive learning for clustering.

    Neural networks : the official journal of the International Neural Network Society·2025
    Same author

    SARS-CoV-2 Infection Association with Atherosclerotic Plaque Progression at Coronary CT Angiography and Adverse Cardiovascular Events.

    Radiology·2025
    Same author

    Metabolic cardiomyopathy associated with a compound heterozygous variant in NAD(P)HX dehydratase: a case report and literature review.

    Translational pediatrics·2025
    Same author

    Comprehensive analysis of the xbp1 gene in Pacific abalone Haliotis discus hannai: Structure, expression, and role in heat stress response.

    International journal of biological macromolecules·2025
    Same author

    A Semi-Supervised Multi-Region Segmentation Framework of Bladder Wall and Tumor with Wall-Enhanced Self-Supervised Pre-Training.

    Bioengineering (Basel, Switzerland)·2025
    Same author

    Overexpression of apple MdNRT1.7 enhances low nitrogen tolerance via the regulation of ROS scavenging.

    International journal of biological macromolecules·2025
    Same journal

    Mask-guided Asymmetric Contrastive and Semantic Alignment for Unsupervised Person Re-Identification.

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

    Hyperbolic Cycle Alignment for Infrared-Visible Image Fusion.

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

    Learning Gaze Synthesizer via 3D-eye Controlled Diffusion and Cross-domain Feature Alignment.

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

    Underlying Semantic Diffusion for Effective and Efficient In-Context Learning.

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

    DiffRES: Unleashing Text-to-Image Diffusion Models for Generative Referring Expression Segmentation without Information Leakage.

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

    Location Matters: Frequency-Spatial Dual Space Adaptation for Cross-Domain Few-Shot Segmentation.

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

    This study introduces the Hierarchical and Interactive Refinement Network (HIRN) to improve salient object detection by preserving edge structures. HIRN enhances accuracy and semantic understanding, outperforming existing methods on benchmark datasets.

    Area of Science:

    • Computer Vision
    • Deep Learning

    Background:

    • Deep Neural Networks (DNNs) have advanced salient object detection.
    • Down-sampling operations in DNNs cause blurred edges, degrading detection performance.

    Purpose of the Study:

    • To propose a novel Hierarchical and Interactive Refinement Network (HIRN) for improved salient object detection.
    • To preserve and enhance edge structures in salient object detection.

    Main Methods:

    • A multi-stage, dual-path network estimates salient edges and regions from feature maps.
    • An edge-guided inference algorithm refines region predictions using detected edges.

    Main Results:

    • The proposed method enhances weak edge responses and suppresses background false positives.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    673

    Related Experiment Videos

    Last Updated: Dec 5, 2025

    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

    860
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    673
  • HIRN achieves more accurate salient region predictions and semantic edge detection.
  • Experimental results demonstrate significant performance improvements over state-of-the-art approaches.

    • Conclusions:

    • The Hierarchical and Interactive Refinement Network (HIRN) effectively addresses edge blurring in salient object detection.
    • The proposed edge-guided inference refines salient maps for superior accuracy.
    • HIRN represents a significant advancement in salient object detection technology.