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

KL-6 levels in the connective tissue disease population: typical values and potential confounders-a retrospective, real-world study.

Frontiers in immunology·2023
Same author

Cancer/testis antigens: promising immunotherapy targets for digestive tract cancers.

Frontiers in immunology·2023
Same author

Down-regulation of peptidylarginine deiminase type 1 in reconstructed human epidermis disturbs nucleophagy in the granular layer and affects barrier function.

Cell death discovery·2023
Same author

Licorice-saponin A3 is a broad-spectrum inhibitor for COVID-19 by targeting viral spike and anti-inflammation.

Journal of pharmaceutical analysis·2023
Same author

Effects of phosphorus species and zinc stress on growth and physiology of the marine diatom Thalassiosira weissflogii.

Chemosphere·2023
Same author

Mueller polarimetric imaging as a tool for detecting the effect of non-thermal plasma treatment on the skin.

Biomedical optics express·2023
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Apr 30, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

917

Discriminative region learning for point cloud-based place recognition.

Hang Yang1, Le Hui2, Yun Zhu1

  • 1School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210000, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 28, 2026
PubMed
Summary
This summary is machine-generated.

We introduce DRFormer, a new method for point cloud place recognition. It enhances feature discriminability by focusing on relevant regions, improving location accuracy.

Keywords:
Deep learningGlobal descriptorPlace recognitionPoint cloud

More Related Videos

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

1.3K
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

8.6K

Related Experiment Videos

Last Updated: Apr 30, 2026

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring
08:16

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

917
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

1.3K
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

8.6K

Area of Science:

  • Computer Vision
  • Robotics
  • Geospatial Analysis

Background:

  • Point cloud place recognition estimates location using global descriptors from local features.
  • Attention mechanisms enhance local features but can aggregate irrelevant information.
  • This aggregation impairs feature discriminative power in place recognition.

Purpose of the Study:

  • To propose a novel discriminative region-guided transformer (DRFormer) for point cloud place recognition.
  • To improve the discriminative power of features by avoiding task-irrelevant information aggregation.
  • To enhance the accuracy of place recognition in point cloud data.

Main Methods:

  • Developed a lightweight global aggregation module (LightVLAD) to identify discriminative regions.
  • Proposed a discriminative region-guided attention module focusing on relevant distant local features.
  • Utilized cross-attention to distribute global information and enhance local features, avoiding distractions.

Main Results:

  • DRFormer effectively identifies and focuses on discriminative regions within point clouds.
  • The method significantly reduces the impact of irrelevant objects and areas on feature representation.
  • Outperformed existing state-of-the-art methods on multiple benchmark datasets for place recognition.

Conclusions:

  • DRFormer enhances point cloud place recognition by focusing on discriminative regions.
  • The proposed attention mechanism improves feature distinctiveness and robustness.
  • This approach offers a more accurate and reliable solution for real-world place recognition tasks.