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: Jun 27, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection.

Tian Qiu1, Jifeng Shen1, Xin Zuo2

  • 1School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China.

Sensors (Basel, Switzerland)
|June 26, 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 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 PNAFusion, a novel method for multispectral object detection that improves feature alignment using pixel-neighborhood attention. PNAFusion offers a practical balance between accuracy and memory usage for resource-constrained applications.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Sensor Fusion

Background:

  • Multispectral object detection faces challenges in aligning and interacting features across different spectra.
  • Global cross-attention methods, while powerful, are computationally expensive for resource-limited platforms.

Purpose of the Study:

  • To develop an efficient multispectral feature fusion framework for object detection.
  • To address the limitations of global cross-attention in terms of computational complexity and handling local misalignments.

Main Methods:

  • Proposes Progressive Pixel-Neighborhood Deformable Cross-Attention (PNAFusion) for multispectral feature fusion.
  • Introduces Pixel-Neighborhood Cross-Attention (PNCA) to focus interaction on relevant areas and reduce noise.
  • Incorporates Adaptive Deformable Alignment (ADA) to capture non-linear spatial correspondences via learned offsets.
Keywords:
cross-modal interactiondeformable attentionfeature alignmentiterative feature fusionmultispectral object detectionpixel-neighborhood attention

More Related Videos

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

Related Experiment Videos

Last Updated: Jun 27, 2026

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

  • Employs an iterative feedback mechanism for progressive cross-modal feature alignment refinement.

    • Main Results:

    • PNAFusion achieved competitive mean Average Precision (mAP) scores on benchmark datasets (FLIR, M3FD, DroneVehicle) when integrated with YOLOv5 and Co-DETR detectors.
    • Demonstrated significant reductions in GPU memory allocation (33.0%) and theoretical FLOPs compared to existing methods like ICAFusion.
    • Showcased a practical accuracy-memory trade-off, making it suitable for resource-constrained environments.

    Conclusions:

    • PNAFusion effectively enhances multispectral object detection by improving feature alignment and interaction efficiency.
    • The proposed method provides a viable solution for deploying advanced object detection on platforms with limited computational resources.
    • PNAFusion represents a significant step towards practical and efficient multispectral object detection systems.