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: Mar 7, 2026

Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects
06:36

Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects

Published on: October 18, 2024

1.5K

View-Based 3-D Model Retrieval: A Benchmark.

An-An Liu, Wei-Zhi Nie, Yue Gao

    IEEE Transactions on Cybernetics
    |February 18, 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

    The effectiveness of vitrified zygote banking for managing the severe diminished ovarian reserve in infertile women: A retrospective cohort study.

    Taiwanese journal of obstetrics & gynecology·2026
    Same author

    Integrative analysis of fitness and metabolic effects of a large multidrug-resistant plasmid in <i>Salmonella</i> across diverse serovars.

    Microbial genomics·2026
    Same author

    Programmable In Vivo Synthesis of Quantum Dots.

    Angewandte Chemie (International ed. in English)·2026
    Same author

    SpineVLM: A Markdown-Guided Structured Fine-Tuning Framework for Spine X-ray Report Generation.

    IEEE journal of biomedical and health informatics·2026
    Same author

    Simultaneous Localization of Electrons/Holes by Surface Cationic Dangling-Bonds/Vacancies for Synergistically Boosting Photocatalytic Activity.

    Journal of the American Chemical Society·2026
    Same author

    Lipid Nanoparticle Encapsulated Chemotherapeutic Drugs Quantitation In vivo using Liquid Chromatography-coupled Electrospray Ionization Tandem Mass Spectrometry.

    Journal of physiological investigation·2026
    Same journal

    Relaxed Stability Conditions for Model Predictive Control of Hybrid Dynamical Systems Using Hybrid Recurrent Neural Networks.

    IEEE transactions on cybernetics·2026
    Same journal

    An Evolutionary Algorithm Assisted by an Ensemble of Pareto-Optimal Surrogate Models.

    IEEE transactions on cybernetics·2026
    Same journal

    A Quantum Self-Attention Neural Network Model on Quantum Circuits.

    IEEE transactions on cybernetics·2026
    Same journal

    Semi-Explicit Solution of Some Discrete-Time Higher-Order-Cost Mean-Field-Type Control.

    IEEE transactions on cybernetics·2026
    Same journal

    A Novel One-Step Small Object Detector for Autonomous Aerial Vehicles.

    IEEE transactions on cybernetics·2026
    Same journal

    Online Data-Driven-Based Optimal Output Tracking Control Without Initial Stabilizing Policy.

    IEEE transactions on cybernetics·2026
    See all related articles

    This study introduces a benchmark for view-based 3-D model retrieval, finding that clique graph matching with deep learning features excels. This advances computer vision techniques and 3-D model analysis.

    Area of Science:

    • Computer Vision
    • 3-D Model Retrieval

    Background:

    • View-based 3-D model retrieval is crucial for computer vision applications.
    • Existing methods lack a standardized benchmark for evaluation.

    Purpose of the Study:

    • To establish a benchmark for evaluating state-of-the-art 3-D model retrieval methods.
    • To propose and assess a novel clique graph-based retrieval technique.

    Main Methods:

    • Reimplementation of six representative 3-D model retrieval methods.
    • Evaluation of hand-crafted and deep features on diverse datasets (NTU60, NTU216, PSB, ETH, MV-RED).
    • Proposal of a clique graph-based retrieval method.

    Main Results:

    • Graph matching methods, particularly with deep features, demonstrate superior performance.

    More Related Videos

    Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data
    11:09

    Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data

    Published on: February 25, 2021

    4.0K
    3D Printing Model of a Patient's Specific Lumbar Vertebra
    07:30

    3D Printing Model of a Patient's Specific Lumbar Vertebra

    Published on: April 14, 2023

    2.6K

    Related Experiment Videos

    Last Updated: Mar 7, 2026

    Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects
    06:36

    Author Spotlight: Insights into the Analysis of Human Interaction with 3D Virtual Objects

    Published on: October 18, 2024

    1.5K
    Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data
    11:09

    Construction of a Realistic, Whole-Body, Three-Dimensional Equine Skeletal Model using Computed Tomography Data

    Published on: February 25, 2021

    4.0K
    3D Printing Model of a Patient's Specific Lumbar Vertebra
    07:30

    3D Printing Model of a Patient's Specific Lumbar Vertebra

    Published on: April 14, 2023

    2.6K
  • The clique graph matching algorithm using convolutional neural network features shows high efficacy.
  • Quantitative analysis across multiple datasets provides performance insights.

    • Conclusions:

    • The clique graph matching algorithm with deep features is a leading approach for view-based 3-D model retrieval.
    • The developed benchmark facilitates future research and method comparison.
    • Further research directions in 3-D model retrieval are identified.