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 25, 2026

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies
07:34

Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies

Published on: November 7, 2025

Pixel-Level RGBT Fusion Tracking via Heterogeneous Multi-Expert Distillation and Decoupled Representation Learning.

Andong Lu, Yuanzhi Guo, Kunpeng Wang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |June 22, 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

    Exploration of the Clinical Assessment and Prognostic Value of Society for Cardiovascular Angiography and Intervention Shock Staging in Patients With Acute Myocardial Infarction and Cardiogenic Shock on Veno-arterial Extracorporeal Membrane Oxygenation Support.

    Reviews in cardiovascular medicine·2026
    Same author

    Unveiling the Power of Multi-Modal Template Update in RGBT Tracking.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    ECMO management in cardiogenic shock-specialized versus non-cardiogenic shock-specialized centers: a registry-based analysis.

    BMC anesthesiology·2025
    Same author

    Clinical study of area-decreasing technique and conventional post-closure technique for V-A ECMO weaning application: study protocol of a randomised controlled trial.

    BMJ open·2025
    Same author

    Prophylactic VA-ECMO During Complex High-Risk PCI: A Randomized Controlled Trial.

    JACC. Advances·2025
    Same author

    AFTER: Attention-Based Fusion Router for RGBT Tracking.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
    Same journal

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    GoP-based Quality Enhancement on Video Compression.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces the Task-driven Pixel-level Fusion tracker (TPF) for RGB-Thermal (RGBT) tracking. TPF enhances early fusion efficiency and discriminative capacity, outperforming existing methods in accuracy and speed.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Robotics

    Background:

    • Pixel-level fusion in RGB-Thermal (RGBT) tracking is efficient but limited by shallow representational capacity.
    • Existing analyses of pixel-level fusion's limitations and potential are insufficient.
    • This work systematically investigates fusion location, modality alignment, and tracking performance.

    Purpose of the Study:

    • To propose a novel Task-driven Pixel-level Fusion tracker (TPF) that enhances the discriminative capacity of pixel-level fusion while maintaining efficiency.
    • To address the limitations of shallow representational capacity and task-relevant discrimination in pixel-level fusion.
    • To offer new insights into efficient and effective RGBT tracking strategies.

    Main Methods:

    • Developed a lightweight pixel fusion adapter for real-time image fusion with minimal parameter overhead (14.3KB).

    Related Experiment Videos

    Last Updated: Jun 25, 2026

    Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies
    07:34

    Utilizing vmTracking to Improve the Accuracy of Multi-Animal Pose Estimation in Rodent Social Behavior Studies

    Published on: November 7, 2025

  • Implemented a task-driven progressive learning framework with heterogeneous multi-expert distillation and decoupled representation learning.
  • Incorporated a nearest-neighbor dynamic template update mechanism for improved robustness.

    • Main Results:

    • TPF achieves competitive accuracy and speed on four RGBT tracking benchmarks.
    • The proposed methods enhance discriminative capacity and overcome generalization limitations.
    • TPF outperforms both feature-level and existing pixel-level fusion methods.

    Conclusions:

    • Pixel-level fusion can be enhanced to achieve high performance in RGBT tracking.
    • The TPF tracker offers an efficient and effective solution for RGBT tracking tasks.
    • This research provides valuable insights into optimizing early fusion strategies for visual tracking.