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: Feb 23, 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

1.1K

Crafting GBD-Net for Object Detection.

Xingyu Zeng, Wanli Ouyang, Junjie Yan

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |September 1, 2017
    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

    [Study on effect of coptidis rhizoma on red blood cells of normal mice and its antioxidant property].

    Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2013
    Same author

    General framework to histogram-shifting-based reversible data hiding.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2013
    Same author

    The prevalences of Neisseria gonorrhoeae and Chlamydia trachomatis infections among female sex workers in China.

    BMC public health·2013
    Same author

    [Study on allocation rules of common nutrients in Scutellaria baicalensis in different phenological periods by ICP-OES].

    Guang pu xue yu guang pu fen xi = Guang pu·2013
    Same author

    Sesterterpenoids.

    Natural product reports·2013
    Same author

    14-3-3 sigma is a useful immunohistochemical marker for diagnosing ovarian granulosa cell tumors and steroid cell tumors.

    International journal of gynecological pathology : official journal of the International Society of Gynecological Pathologists·2013
    Same journal

    Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

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

    Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

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

    TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

    SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

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

    HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

    Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

    IEEE transactions on pattern analysis and machine intelligence·2026
    See all related articles

    This study introduces Gated Bi-directional CNN (GBD-Net) for object detection. GBD-Net effectively integrates local and contextual visual cues by enabling message passing between support regions, improving detection accuracy.

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Machine Learning

    Background:

    • Object detection relies on integrating visual cues from various support regions.
    • Effective fusion of local and contextual information remains a challenge in object detection.

    Purpose of the Study:

    • To propose a novel Gated Bi-directional CNN (GBD-Net) for enhanced object detection.
    • To enable effective message passing among features from different support regions.

    Main Methods:

    • Developed GBD-Net, a CNN architecture facilitating bi-directional message passing between support regions.
    • Implemented gated functions to dynamically control message transmission based on input sample evidence.
    • Applied the GBD-Net in conjunction with techniques like multi-scale testing and NMS.

    More Related Videos

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
    05:41

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

    Published on: February 6, 2020

    9.9K

    Related Experiment Videos

    Last Updated: Feb 23, 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

    1.1K
    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
    05:41

    A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

    Published on: February 6, 2020

    9.9K

    Main Results:

    • GBD-Net demonstrated effectiveness across ImageNet, Pascal VOC2007, and Microsoft COCO datasets.
    • The proposed method achieved success in the ImageNet object detection challenge 2016.
    • Analysis showed that message passing is sample-dependent, necessitating gated control.

    Conclusions:

    • GBD-Net provides a robust framework for integrating local and contextual visual cues in object detection.
    • The gated mechanism allows for adaptive message passing, optimizing performance.
    • The study offers a comprehensive winning system for object detection challenges.