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 10, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.7K

Unsupervised Trademark Retrieval Method Based on Attention Mechanism.

Jiangzhong Cao1, Yunfei Huang1, Qingyun Dai2

  • 1School of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China.

Sensors (Basel, Switzerland)
|April 3, 2021
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

Fitness-for-Service Assessment of Dent Defects on Steel Energy Pipelines: Evaluation Criteria, Integrity Prediction, and Future Challenges.

Materials (Basel, Switzerland)·2026
Same author

An autonomous AI agent for knowledge and data cooperation in ED clinical decision support.

NPJ digital medicine·2026
Same author

Development of a predictive nomogram for perioperative lower extremity deep vein thrombosis in patients with breast cancer and the efficacy of dextran 40 prophylaxis.

American journal of cancer research·2026
Same author

Magnolol ameliorates Streptococcus suis serotype 2-induced pulmonary inflammatory injury in mice via inhibition of GSDMD.

Microbial pathogenesis·2026
Same author

Simulation Effect and Mechanism of High-Polymeric Persimmon Tannin on Simulating Alternate-Day Fasting on Regulating Lipid Metabolism in Obese Mice.

Nutrients·2026
Same author

Effects of Controlled-Release Fertilizer Application Rate on Growth, Physiological Traits, and Chlorophyll Fluorescence Responses of <i>Paeonia delavayi</i> Seedlings.

Plants (Basel, Switzerland)·2026
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

This study introduces an unsupervised trademark retrieval method using an attention mechanism to improve feature relevance and reduce labeling costs. The novel approach significantly enhances trademark retrieval performance compared to existing methods.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Existing trademark retrieval methods face challenges with high data labeling costs.
  • Internal feature relevance is often overlooked in current trademark retrieval techniques.
  • Supervised learning methods can be resource-intensive and may not fully capture feature importance.

Purpose of the Study:

  • To propose an unsupervised trademark retrieval method that addresses the limitations of existing approaches.
  • To enhance the internal relevance of features within trademark representations.
  • To reduce the overall cost associated with data labeling for trademark retrieval systems.

Main Methods:

  • An instance discrimination framework is employed for unsupervised feature learning.
Keywords:
attention mechanisminstance discriminationlocal cross-channel interactiontrademark retrieval

More Related Videos

Methods to Test Visual Attention Online
09:44

Methods to Test Visual Attention Online

Published on: February 19, 2015

12.1K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.9K

Related Experiment Videos

Last Updated: Nov 10, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.7K
Methods to Test Visual Attention Online
09:44

Methods to Test Visual Attention Online

Published on: February 19, 2015

12.1K
A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

7.9K
  • A lightweight attention mechanism is integrated to assign optimal weights to critical features.
  • The method focuses on learning robust feature representations without manual labeling.

    • Main Results:

    • The proposed unsupervised method achieves superior trademark retrieval performance.
    • Experimental results on the METU trademark dataset demonstrate significant improvements over traditional and supervised methods.
    • A low Normalized Average Rank (NAR) of 0.051 was achieved, validating the method's effectiveness.

    Conclusions:

    • The unsupervised attention-based trademark retrieval method offers a cost-effective and efficient solution.
    • The approach effectively captures and utilizes key features for improved retrieval accuracy.
    • This method represents a significant advancement in unsupervised learning for trademark retrieval applications.