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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Design, synthesis, biological evaluation, DFT and molecular docking studies of novel isoxazolines containing cyclic amide.

Bioorganic chemistry·2026
Same author

Air-permeable hydrogels through viscoelastic phase separation of aerogels.

Nature·2026
Same author

Post-stroke acute heart failure in patients with large vessel occlusion undergoing endovascular treatment: A pooled analysis of individual patient data from multicenter studies with mediation analysis.

PLoS medicine·2026
Same author

High-definition transcranial direct current stimulation enhances exercise-induced hypoalgesia in patients with chronic low back pain.

iScience·2026
Same author

PEGylated thymosin β4 is a thiol-site-specific prodrug treating myocardial infarction in vivo.

Bioengineering & translational medicine·2026
Same author

High-Redox-Potential p-Type Covalent Organic Frameworks With Abundant Active Sites for High-Voltage and Long-Life Lithium-Ion Battery Cathodes.

Angewandte Chemie (International ed. in English)·2026

Related Experiment Video

Updated: Oct 29, 2025

Creating Objects and Object Categories for Studying Perception and Perceptual Learning
14:38

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

12.0K

Modeling Cardinality in Image Hashing.

Dayong Tian, Chen Gong, Maoguo Gong

    IEEE Transactions on Cybernetics
    |July 8, 2021
    PubMed
    Summary

    This study introduces a novel method for unsupervised image hashing by incorporating cardinality constraints. Estimating the number of nonzero outputs improves image classification performance.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Cardinality constraints are effective in structural learning and modeling multidimensional label dependencies.
    • Estimating the number of nonzero outputs (cardinality) can enhance classification performance compared to direct prediction.
    • Unsupervised image hashing generates binary codes, analogous to multidimensional labels, benefiting from cardinality estimation.

    Purpose of the Study:

    • To integrate cardinality constraints into unsupervised image hashing.
    • To improve the performance of unsupervised image hashing models.

    Main Methods:

    • A two-step approach: 1) estimating hashing code cardinalities and 2) predicting the bits that are 1.
    • Utilizing a neural network as a cardinality predictor.

    More Related Videos

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    43.1K
    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
    08:27

    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

    Published on: January 5, 2024

    1.3K

    Related Experiment Videos

    Last Updated: Oct 29, 2025

    Creating Objects and Object Categories for Studying Perception and Perceptual Learning
    14:38

    Creating Objects and Object Categories for Studying Perception and Perceptual Learning

    Published on: November 2, 2012

    12.0K
    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
    13:44

    Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

    Published on: August 30, 2013

    43.1K
    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
    08:27

    Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

    Published on: January 5, 2024

    1.3K
  • Jointly learning the cardinality predictor and an autoencoder-based hashing code generator.

    • Main Results:

    • The proposed method effectively incorporates cardinality constraints into unsupervised image hashing.
    • Experimental results demonstrate the efficiency and improved performance of the proposed approach.

    Conclusions:

    • Cardinality constraint is a valuable addition to unsupervised image hashing.
    • Jointly learning cardinality prediction with hashing code generation enhances model performance.