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: Sep 9, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K

GIMS: Image matching system based on adaptive graph construction and graph neural network.

Xianfeng Song1, Yi Zou1, Zheng Shi1

  • 1School of Microelectronics, South China University of Technology, Guangdong, China.

Neural Networks : the Official Journal of the International Neural Network Society
|September 4, 2025
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

Leveraging direct learning and reinforcement learning architectures for pre-equalization in high-speed VLC systems.

Optics express·2026
Same author

Development and application of an improved constitutive model for acidizing coal around fractured boreholes.

Scientific reports·2025
Same author

Centrifugal microfluidic chip with an air gap for oil-free production of enhanced adipogenic multicellular microspheres.

Lab on a chip·2025
Same author

Research on the Bearing Remaining Useful Life Prediction Method Based on Optimized BiLSTM.

Sensors (Basel, Switzerland)·2025
Same author

Targeted Isolation of ω-3 Polyunsaturated Fatty Acids from the Marine Dinoflagellate <i>Prorocentrum lima</i> Using DeepSAT and LC-MS/MS and Their High Activity in Promoting Microglial Functions.

Marine drugs·2025
Same author

Association of grey matter cerebral blood flow with white matter integrity in relation to youth bipolar disorder.

Journal of psychiatry & neuroscience : JPN·2025
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

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

Decentralized ADMM for factorization-based Low-rank matrix estimation.

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

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

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

Q-learning based asynchronous Boolean control networks stabilization with data loss.

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

New results on prescribed-time synchronization of complex networks via intermittent control.

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

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces an adaptive graph construction method for feature-based image matching using Graph Neural Networks (GNNs) and Transformers. The novel approach significantly enhances matching performance and efficiency.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Graph Neural Networks

Background:

  • Feature-based image matching is crucial for computer vision tasks.
  • Graph Neural Networks (GNNs) offer superior performance over traditional methods for keypoint representation.
  • Existing GNN approaches for image matching face challenges in graph construction and feature representation.

Purpose of the Study:

  • To develop an innovative adaptive graph construction method for enhanced image matching.
  • To integrate GNNs with Transformers for improved spatial and feature information representation.
  • To achieve state-of-the-art performance in feature-based image matching.

Main Methods:

  • Introduced an adaptive graph construction using distance and dynamic threshold similarity filtering.
Keywords:
Graph matchingGraph neural networkImage matchingMachine learning

More Related Videos

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

633

Related Experiment Videos

Last Updated: Sep 9, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
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

633
  • Combined Graph Neural Networks (GNNs) with Transformers for hybrid feature representation.
  • Utilized the Sinkhorn algorithm for optimal matching and multi-GPU for accelerated training.

    • Main Results:

    • Achieved an average improvement of 3.8×-40.3× in overall matching performance.
    • Demonstrated the effectiveness of the adaptive graph construction and hybrid model.
    • Validated the system's performance on extensive image datasets through comparative experiments.

    Conclusions:

    • The proposed GNN-Transformer hybrid model with adaptive graph construction significantly advances feature-based image matching.
    • The method offers robust and precise graph structures, improving matching accuracy.
    • Efficient training achieved through multi-GPU technology, addressing computational demands.