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: Nov 6, 2025

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

736

A Supervised Video Hashing Method Based on a Deep 3D Convolutional Neural Network for Large-Scale Video Retrieval.

Hanqing Chen1, Chunyan Hu2, Feifei Lee1

  • 1Shanghai Engineering Research Center of Assistive Devices, School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.

Sensors (Basel, Switzerland)
|May 5, 2021
PubMed
Summary

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

Vasicine-Based Synergistic Antifungal Agents against FLC-Resistant <i>Candida albicans</i> Targeting Ras/cAMP/PKA Pathway.

ACS medicinal chemistry letters·2026
Same author

The Effectiveness of Three Steps Training in Clinical Reasoning for Clerkship Medical Students, a Pilot Trial in Nephrology Department.

Medical science educator·2026
Same author

Ultrasound-guided, nursing-led, phase-based swallowing rehabilitation in elderly patients with MIBG-positive medullary thyroid carcinoma following <sup>131</sup>I-MIBG therapy.

Frontiers in medicine·2026
Same author

Durable Core-Shell Scatterer Coating with Heat Storage for Radiative Cooling.

ACS applied materials & interfaces·2026
Same author

An interpretable predictive model for depression risk in diabetic patients: A web-based application using NHANES data.

Medicine·2026
Same author

GSDMD/Caspase-1-based evaluation of dydrogesterone in preventing recurrence after hysteroscopic endometrial polypectomy.

Clinics (Sao Paulo, Brazil)·2026

Deep supervised video hashing (DSVH) improves video retrieval speed and precision by using 3D CNNs for spatial-temporal features and supervised hashing to generate compact binary codes for efficient searching.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Multimedia Retrieval

Background:

  • The proliferation of online videos necessitates efficient content-based video retrieval (CBVR) systems.
  • Existing CBVR methods often neglect temporal information by relying on single-frame features.
  • Hashing techniques, while efficient, are predominantly applied to image retrieval, not video.

Purpose of the Study:

  • To develop an end-to-end framework for fast and accurate content-based video retrieval.
  • To address the limitations of previous methods in capturing spatio-temporal video features.
  • To enhance the efficiency of video retrieval using hashing techniques.

Main Methods:

  • Implemented a deep supervised video hashing (DSVH) framework.
  • Utilized a 3D convolutional neural network (CNN) to extract spatio-temporal video features.
Keywords:
3D CNNsupervised hashingtriplet lossvideo retrieval

More Related Videos

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.2K

Related Experiment Videos

Last Updated: Nov 6, 2025

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

736
Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
08:25

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

9.2K
  • Employed supervised hashing and triplet loss for training hash functions and generating compact binary codes.

    • Main Results:

    • Achieved superior performance on UCF-101, JHMDB, and HMDB-51 datasets compared to state-of-the-art methods.
    • Demonstrated significant improvements in mean average precision (mAP), with a 9.3% increase on UCF-101.
    • Showcased the algorithm's stability and effectiveness in video retrieval tasks.

    Conclusions:

    • The proposed DSVH method effectively captures spatio-temporal features for improved video retrieval.
    • DSVH offers a robust and efficient solution for large-scale video retrieval challenges.
    • The framework provides a significant advancement in the field of content-based video retrieval.