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: 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

1.2K

Supervised Learning of Semantics-Preserving Hash via Deep Convolutional Neural Networks.

Huei-Fang Yang, Kevin Lin, Chu-Song Chen

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |February 17, 2017
    PubMed
    Summary

    This study introduces supervised semantics-preserving deep hashing (SSDH), a novel method for generating binary hash codes from labeled data for efficient large-scale image search. SSDH unifies classification and retrieval, outperforming existing hashing techniques in accuracy without compromising classification performance.

    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

    Orobas: A computational approach for scoring and analysis of quantitative chemical-genetic interactions from CRISPR-Cas9 screens.

    STAR protocols·2026
    Same author

    HRDetect in Tubo-ovarian Carcinoma: Stratification and Therapeutic Implications.

    Clinical cancer research : an official journal of the American Association for Cancer Research·2026
    Same author

    Cardiorenal Syndrome Type 1 Complicated by Uremic Pericarditis and a Small Pericardial Effusion Causing Cardiac Tamponade.

    Cureus·2026
    Same author

    Single-cell imaging analysis, therapeutic modeling and a Phase Ib trial validate BCL-2 as a target across heterogeneous castration-resistant prostate cancer.

    Signal transduction and targeted therapy·2026
    Same author

    Global genetic interaction network of a human cell maps conserved principles and informs functional interpretation of gene co-essentiality profiles.

    Cell·2026
    Same author

    Integrating addiction care in hepatology: Impact of liver consultation on post-discharge AUD treatment in alcohol-associated hepatitis.

    Journal of substance use and addiction treatment·2026

    Area of Science:

    • Computer Science
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Large-scale image search requires efficient methods for representing and retrieving visual data.
    • Traditional hashing methods often struggle to balance retrieval accuracy with semantic understanding.
    • Supervised learning offers potential for improving hash code generation by incorporating label information.

    Purpose of the Study:

    • To develop a supervised deep hashing approach for large-scale image search.
    • To unify image classification and retrieval within a single learning model.
    • To create binary hash codes that preserve semantic information effectively.

    Main Methods:

    • Proposed supervised semantics-preserving deep hashing (SSDH) approach.
    • Constructed hash functions as a latent layer within a deep neural network.

    More Related Videos

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

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    10.1K

    Related Experiment Videos

    Last Updated: Mar 7, 2026

    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

    1.2K
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    10.1K
  • Minimized an objective function balancing classification error and hash code properties.
  • Employed joint learning of image representations, hash codes, and classification.

    • Main Results:

    • SSDH effectively constructs binary hash codes from labeled data.
    • The approach unifies classification and retrieval in a single model.
    • SSDH demonstrates scalability to large-scale datasets through point-wise learning.
    • Achieved higher retrieval accuracy compared to state-of-the-art hashing methods.
    • Maintained classification performance while improving retrieval.

    Conclusions:

    • SSDH offers a simple yet effective supervised deep hashing solution for large-scale image search.
    • The method successfully integrates semantic label information into hash code generation.
    • SSDH provides a scalable and high-performance alternative to existing hashing techniques.