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: May 16, 2026

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
08:04

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

View-based discriminative probabilistic modeling for 3D object retrieval and recognition.

Meng Wang1, Yue Gao, Ke Lu

  • 1School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230009, China.

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|December 11, 2012
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

Intercalation-Coupled Zn<sup>2+</sup> Transfer Enables Reversible ZnS Conversion in Aqueous Zn-S Batteries.

Nano letters·2026
Same author

Dietary alanine or glycine improves feed utilization and modulates gut-liver physiological responses in largemouth bass fed a low-fishmeal diet.

Comparative biochemistry and physiology. Part B, Biochemistry & molecular biology·2026
Same author

Tuning Sulfur Reduction via Unique Radical-Mediated Solid-Liquid-Solid Pathway for High-Rate Aqueous Zn-S Batteries.

Nano letters·2026
Same author

Knockout of bsal/cel.2 results in growth retardation, reduced lipid digestion and altered energy metabolism in medaka larvae (oryzias latipes).

Functional & integrative genomics·2026
Same author

Training-Free Open-Set Domain Adaptation With Vision-Language Models.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
Same author

DreamAssemble: Complex Multi-Object Text-to-3D Generation via Multi-Density Neural Fields.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

This study introduces a novel probabilistic object modeling approach for 3D object recognition and retrieval. It improves distance estimation between 3D objects by defining it as the Kullback-Leibler divergence of their probabilistic models.

Area of Science:

  • Computer Vision
  • Machine Learning
  • 3D Object Recognition

Background:

  • View-based 3D object recognition relies on multiple object views.
  • Estimating distances between objects is crucial for retrieval and recognition.
  • Conventional methods often integrate pairwise view distances, which can be suboptimal.

Purpose of the Study:

  • To propose a discriminative probabilistic object modeling approach for improved 3D object retrieval and recognition.
  • To define a novel distance measure between objects based on probabilistic models.
  • To enhance the discriminative ability of object models.

Main Methods:

  • Building probabilistic models for each object from its view distributions.
  • Defining object distance as the upper bound of Kullback-Leibler divergence between models.

Related Experiment Videos

Last Updated: May 16, 2026

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues
08:04

Measuring Sensitivity to Viewpoint Change with and without Stereoscopic Cues

Published on: December 4, 2013

  • Learning object models via adaptation from global models using maximum likelihood, followed by a discriminative adaptation step.

    • Main Results:

    • The proposed approach demonstrates superior performance in 3D object retrieval and recognition.
    • Experimental results on benchmark datasets (ETH 3D, NTU 3D, Princeton Shape Benchmark) validate the method's effectiveness.
    • The discriminative adaptation step significantly enhances model performance.

    Conclusions:

    • The discriminative probabilistic object modeling approach offers a more effective way to estimate distances between 3D objects.
    • This method advances the state-of-the-art in view-based 3D object retrieval and recognition.
    • The Kullback-Leibler divergence of probabilistic models provides a robust measure for object comparison.