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: Jan 19, 2026

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

2.2K

ME R-CNN: Multi-Expert R-CNN for Object Detection.

Hyungtae Lee, Sungmin Eum, Heesung Kwon

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |September 11, 2019
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping09:41

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

    2.2K
    When we grasp an object, multiple regions of the fingers and hand typically make contact with the object's surface. Reconstructing such contact regions is challenging. Here, we present a method for approximately estimating the contact regions by combining marker-based motion capture with existing deep learning-based hand mesh...
    2.2K
    Detecting Pre-Stimulus Source-Level Effects on Object Perception with Magnetoencephalography09:25

    Detecting Pre-Stimulus Source-Level Effects on Object Perception with Magnetoencephalography

    7.3K
    This article describes how to set up an experiment that allows detecting pre-stimulus source-level influences on object perception using magnetoencephalography (MEG). It covers stimulus material, experimental design, MEG recording, and data...
    7.3K
    End-To-End Deep Neural Network for Salient Object Detection in Complex Environments03:31

    End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

    1.0K
    The present protocol describes a novel end-to-end salient object detection algorithm. It leverages deep neural networks to enhance the precision of salient object detection within intricate environmental...
    1.0K
    Subnanometer-resolution Structural Determination of Hemagglutinin from Cryo-electron Tomography of Influenza Viruses08:19

    Subnanometer-resolution Structural Determination of Hemagglutinin from Cryo-electron Tomography of Influenza Viruses

    602
    This article presents a protocol for data processing of influenza viruses imaged using cryo-electron tomography and subsequent subtomogram averaging of the hemagglutinin glycoprotein. This protocol covers step-by-step data processing, from image preprocessing to final model...
    602
    Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence09:11

    Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

    2.7K
    The micronucleus (MN) assay is a well-established test for quantifying DNA damage. However, scoring the assay using conventional techniques such as manual microscopy or feature-based image analysis is laborious and challenging. This paper describes the methodology to develop an artificial intelligence model to score the MN assay using imaging flow cytometry...
    2.7K
    Creating Objects and Object Categories for Studying Perception and Perceptual Learning14:38

    Creating Objects and Object Categories for Studying Perception and Perceptual Learning

    12.2K
    We describe a novel methodology for creating naturalistic 3-D objects and object categories with precisely defined feature variations. We use simulations of the biological processes of morphogenesis and phylogenesis to create novel, naturalistic virtual 3-D objects and object categories that can then be rendered as visual images or haptic...
    12.2K

    You might also read

    Related Articles

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

    Sort by
    Same author

    A Multi-Purpose Realistic Haze Benchmark With Quantifiable Haze Levels and Ground Truth.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
    Same author

    DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors.

    IEEE transactions on pattern analysis and machine intelligence·2019
    Same author

    Going Deeper With Contextual CNN for Hyperspectral Image Classification.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2017
    Same author

    Kernel matched subspace detectors for hyperspectral target detection.

    IEEE transactions on pattern analysis and machine intelligence·2006
    Same author

    Automated vehicle detection in forward-looking infrared imagery.

    Applied optics·2004
    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 developed a Multi-Expert Region-based Convolutional Neural Network (ME R-CNN) with an expert assignment network (EAN) to improve object detection. This approach effectively handles appearance variations in regions of interest (RoIs) for better accuracy.

    Area of Science:

    • Computer Vision
    • Deep Learning
    • Machine Learning

    Background:

    • Object detection models often struggle with appearance variations in regions of interest (RoIs) due to differences in shape, pose, and viewing angle.
    • Existing architectures may not optimally adapt to diverse RoI characteristics, limiting detection performance.
    • The need for specialized processing of varied RoIs in complex visual scenes is critical.

    Purpose of the Study:

    • To introduce a novel Multi-Expert Region-based Convolutional Neural Network (ME R-CNN) designed to enhance object detection accuracy.
    • To develop an automated Expert Assignment Network (EAN) for optimally directing regions of interest (RoIs) to specialized processing units.
    • To propose an effective end-to-end training strategy for the integrated ME R-CNN and EAN architecture.

    Main Methods:

    More Related Videos

    Detecting Pre-Stimulus Source-Level Effects on Object Perception with Magnetoencephalography
    09:25

    Detecting Pre-Stimulus Source-Level Effects on Object Perception with Magnetoencephalography

    Published on: July 26, 2019

    7.3K
    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

    1.0K

    Related Experiment Videos

    Last Updated: Jan 19, 2026

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
    09:41

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

    Published on: April 21, 2023

    2.2K
    Detecting Pre-Stimulus Source-Level Effects on Object Perception with Magnetoencephalography
    09:25

    Detecting Pre-Stimulus Source-Level Effects on Object Perception with Magnetoencephalography

    Published on: July 26, 2019

    7.3K
    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

    1.0K
    • The proposed ME R-CNN utilizes multiple specialized 'expert' networks, each trained to process specific types of RoIs.
    • An innovative, learnable Expert Assignment Network (EAN) is introduced to dynamically assign RoIs to the most suitable expert.
    • A tailored, end-to-end training strategy is devised to optimize the interdependent ME R-CNN, EAN, and shared network components.

    Main Results:

    • The ME R-CNN architecture demonstrates a significant performance improvement over baseline models.
    • The EAN effectively learns optimal RoI-expert relationships, even without explicit supervision.
    • Evaluations on PASCAL VOC 07, 12, and MS COCO datasets confirm the substantial gains in detection accuracy.

    Conclusions:

    • The Multi-Expert Region-based Convolutional Neural Network (ME R-CNN) with an Expert Assignment Network (EAN) offers a robust solution for handling appearance variations in object detection.
    • The proposed architecture and training strategy lead to considerable performance enhancements on benchmark datasets.
    • This work provides a foundation for more adaptive and accurate deep learning models in computer vision tasks.