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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Engineering a nanocluster-immobilized MOF@MOF architecture-based ratiometric fluorescence bioassay for sensing neurodegenerative disease-related acetylcholinesterase and inhibitor drugs.

Analytical methods : advancing methods and applications·2026
Same author

MonSter++: Unified Stereo Matching, Multi-View Stereo, and Real-Time Stereo With Monodepth Priors.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Expression of YTHDF1 and YTHDF2 in lung squamous cell carcinoma and their correlation with PD-L1.

Journal of thoracic disease·2026
Same author

Compositionally-informed machine learning for solid-state electrolyte design: a structure-free approach.

Nanoscale·2026
Same author

Corrigendum to "VV-ECMO-supported management of severe ARDS secondary to melioidosis sepsis: A case report and concise review" [IDCases 44 (2026) e02612].

IDCases·2026
Same author

VV-ECMO-supported management of severe ARDS secondary to melioidosis sepsis: A case report and concise review.

IDCases·2026

Related Experiment Video

Updated: Oct 7, 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

674

Learning Discriminative Cross-Modality Features for RGB-D Saliency Detection.

Fengyun Wang, Jinshan Pan, Shoukun Xu

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |January 11, 2022
    PubMed
    Summary

    This study introduces a novel RGB-D saliency detection method that effectively bridges the modality gap by learning discriminative cross-modality features. The approach enhances saliency detection accuracy by fusing RGB and depth information through a unique correlation-fusion mechanism.

    More Related Videos

    Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking
    05:58

    Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking

    Published on: August 29, 2018

    9.0K
    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

    Published on: May 7, 2019

    9.1K

    Related Experiment Videos

    Last Updated: Oct 7, 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

    674
    Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking
    05:58

    Using Rapid Serial Visual Presentation to Measure Set-Specific Capture, a Consequence of Distraction While Multitasking

    Published on: August 29, 2018

    9.0K
    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
    08:25

    Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

    Published on: May 7, 2019

    9.1K

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • RGB-D saliency detection methods face challenges due to the modality gap between RGB and depth images, leading to suboptimal results with simple feature concatenation.
    • Existing approaches primarily focus on bridging this gap via cross-modal fusion modules, often neglecting the explicit extraction of consistent information.
    • There is a need for methods that can effectively learn discriminative cross-modality features and leverage consistent information for improved saliency detection.

    Purpose of the Study:

    • To develop a simple yet effective RGB-D saliency detection method by learning discriminative cross-modality features.
    • To explicitly extract and fuse consistent information from RGB and depth modalities.
    • To improve the accuracy and fine segmentation of salient objects in RGB-D images.

    Main Methods:

    • Learning modality-specific features for RGB and depth inputs.
    • Calculating cross-modality consistent pixel-pair correlations (RGB correlation and depth correlation).
    • Proposing a novel correlation-fusion mechanism to integrate RGB and depth correlations, creating a cross-modality correlation.
    • Refining features using long-range cross-modality correlations for localization and local depth correlations for segmentation.
    • Utilizing a lightweight DepthNet for efficient depth feature extraction.
    • Solving the network in an end-to-end manner.

    Main Results:

    • The proposed method effectively bridges the modality gap by learning discriminative cross-modality features.
    • The correlation-fusion mechanism successfully integrates RGB and depth information.
    • Quantitative and qualitative experimental results demonstrate favorable performance compared to state-of-the-art methods.
    • The method achieves accurate localization and fine segmentation of salient maps.

    Conclusions:

    • The developed RGB-D saliency detection method offers a significant improvement over existing techniques.
    • The novel approach of learning discriminative cross-modality features and correlation-fusion is effective.
    • The method provides a robust solution for accurate and efficient saliency detection in RGB-D data.