Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same authorSame journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

OsGAPC3 modulates starch synthesis and grain chalkiness by integrating glycolysis and transcriptional regulation in rice.

Plant science : an international journal of experimental plant biology·2026

Same author

Study on microstructural evolution of soft clay under one-dimensional consolidation.

Scientific reports·2026

Same author

E2E-OCT: end-to-end joint learning model using optical coherence tomography images for vocal cord leukoplakia diagnosis.

Optics letters·2026

Same author

Interpretable scRNA-seq Analysis with Intelligent Gene Selection.

Applied biochemistry and biotechnology·2026

Same author

Extracellular volume fraction determined by equilibrium contrast-enhanced dual-energy CT as a diagnostic indicator in patients with renal masses.

Journal of cancer research and therapeutics·2026

Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 16, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

A Functional Representation for Graph Matching.

Fu-Dong Wang, Nan Xue, Yipeng Zhang

IEEE Transactions on Pattern Analysis and Machine Intelligence

|May 31, 2019

Summary

This summary is machine-generated.

This study introduces a functional representation for graph matching (FRGM) to address computational challenges in computer vision. FRGM offers geometric insights and improves efficiency for graph correspondence problems.

More Related Videos

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

Related Experiment Videos

Last Updated: Dec 16, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Generating Strictly Controlled Stimuli for Figure Recognition Experiments

Published on: March 18, 2019

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues

Published on: July 14, 2015

Area of Science:

Computer Vision
Pattern Recognition
Graph Theory

Background:

Graph matching is crucial for node correspondence but computationally intensive when using quadratic assignment problems (QAP).
Existing methods face challenges with NP-complete complexity and computational difficulties, especially with pairwise constraints.

Purpose of the Study:

To present a novel Functional Representation for Graph Matching (FRGM) to enhance geometric understanding.
To reduce the space and time complexities associated with graph matching algorithms.
To enable simultaneous estimation of correspondence matrices and geometric deformations.

Main Methods:

Representing graphs within linear function spaces with geometrically meaningful functionals.
Formulating the correspondence matrix as a linear representation map.
Utilizing edge-attributes instead of affinity matrices and employing efficient optimization strategies.

Main Results:

FRGM provides enhanced geometric insights into graph matching.
Reduced space complexity by using edge-attributes.
Achieved state-of-the-art performance on synthetic and real-world datasets.
Demonstrated simultaneous estimation of correspondence and deformations.

Conclusions:

FRGM offers a computationally efficient and geometrically insightful approach to graph matching.
The method effectively handles rigid and nonrigid deformations.
FRGM achieves superior performance compared to existing techniques.