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: May 28, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

MscaVPR: Multi-Scale Coordinate Attention Network for Robust Visual Place Recognition.

Xiaohan Gao1, Zhinong Zhong1, Yongjian Tan1

  • 1College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China.

Sensors (Basel, Switzerland)
|May 27, 2026
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

Large-Scale Quantitative Morphometry of Platelet α-Granules via SIM Super-Resolution Microscopy for Cancer Liquid Biopsy.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Integrated multi-omics analysis reveals the anti-fatigue mechanisms of Shenzhu granules.

Journal of the science of food and agriculture·2026
Same author

High-order modulation signals equalization based on reservoir computing under equivalent-time sampling.

The Review of scientific instruments·2026
Same author

Illuminating Mitochondrial Dynamics: Ultrahigh Labeling Stability Probe for Long-Term SIM Super-Resolution Imaging of Mitochondria.

ACS central science·2025
Same author

Realization of extremely narrow divergence angle and ground test method toward quantum key distribution based on a medium-high orbit satellite.

Applied optics·2025
Same author

Comprehensive network pharmacology and experimental study to investigate the effects and mechanisms of Lophatherum gracile Brongn. for glioma treatment.

Experimental cell research·2025
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

MscaVPR enhances visual place recognition (VPR) by integrating multi-scale features and azimuth-aware training. This approach improves robustness against viewpoint changes, outperforming existing methods on benchmark datasets.

Area of Science:

  • Computer Vision
  • Robotics
  • Geospatial Analysis

Background:

  • Visual place recognition (VPR) is crucial for localization but challenged by appearance variations, viewpoint changes, and perceptual aliasing.
  • Existing VPR methods struggle with adaptive multi-scale feature fusion and viewpoint-aware training, limiting robustness under severe viewpoint shifts.

Purpose of the Study:

  • To propose MscaVPR, a novel framework enhancing VPR robustness through multi-scale feature fusion and azimuth-aware training.
  • To address limitations in existing VPR techniques concerning adaptive feature aggregation and viewpoint generalization.

Main Methods:

  • Incorporation of a Multi-Scale Spatial Pyramid Attention (MSPA) module for aggregating regional features across scales.
  • Utilization of Coordinate Attention (CA) for encoding positional cues and refining spatial features.
Keywords:
multi-scale feature aggregationviewpoint robustnessvisual place recognition

Related Experiment Videos

Last Updated: May 28, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

  • Development of an azimuth-guided training strategy with hard positive sample selection and an azimuth-aware auxiliary loss function.

    • Main Results:

    • MscaVPR demonstrated superior performance compared to strong baselines on multiple benchmark datasets.
    • Significant improvements in Recall@1 were observed: 2.1% on AmsterTime, 1.9% on SVOX-Night, and 1.9% on SVOX-Sun.
    • The framework showed enhanced performance under challenging conditions, particularly with severe viewpoint variations.

    Conclusions:

    • Explicitly incorporating azimuth cues effectively complements existing multi-scale and attention-based VPR methods.
    • The proposed MscaVPR framework offers a robust solution for visual place recognition, especially in scenarios with significant viewpoint discrepancies.
    • The study highlights the importance of viewpoint-aware training strategies for advancing VPR capabilities.