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: Jan 10, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

Quality-Aware Spatio-Temporal Transformer Network for RGBT Tracking.

Zhaodong Ding, Chenglong Li, Tao Wang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |November 27, 2025
    PubMed
    Summary

    This study introduces a Quality-aware Spatio-temporal Transformer Network (QSTNet) for robust Red-Green-Blue-Thermal (RGBT) tracking. QSTNet effectively suppresses low-quality tokens using quality weights, significantly improving tracking performance.

    Related Concept Videos

    Relative Motion Analysis using Rotating Axes01:25

    Relative Motion Analysis using Rotating Axes

    863
    Consider a component AB undergoing a linear motion. Along with a linear motion, point B also rotates around point A. To comprehend this complex movement, position vectors for both points A and B are established using a stationary reference frame.
    However, to express the relative position of point B relative to point A, an additional frame of reference, denoted as x'y', is necessary. This additional frame not only translates but also rotates relative to the fixed frame, making it...
    863

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Differential perovskite hemispherical photodetector for intelligent imaging and location tracking.

    Nature communications·2024
    Same author

    Real-world effectiveness of nirmatrelvir-ritonavir versus azvudine in hospitalized patients with COVID-19 during the omicron wave in Beijing: a multicenter retrospective cohort study.

    BMC infectious diseases·2024
    Same author

    Morphological Profiling for Drug Discovery in the Era of Deep Learning.

    ArXiv·2024
    Same author

    The epigenetic regulatory effect of histone acetylation and deacetylation on skeletal muscle metabolism-a review.

    Frontiers in physiology·2023
    Same author

    A case of brain arteriovenous malformation treated by high-pressure cooker technique assisted with anhydrous alcohol embolization: A case report.

    Medicine·2023
    Same author

    Neutrophil heterogeneity and aging: implications for COVID-19 and wound healing.

    Frontiers in immunology·2023

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Transformer-based RGBT tracking leverages self and cross-attention mechanisms for powerful feature representations.
    • However, these mechanisms are sensitive to low-quality tokens, impacting tracking robustness.

    Purpose of the Study:

    • To propose a novel Quality-aware Spatio-temporal Transformer Network (QSTNet) for robust RGBT tracking.
    • To address the issue of low-quality tokens affecting attention mechanisms in RGBT tracking.

    Main Methods:

    • Developed a Quality-aware Token Weighting Module (QTWM) to calculate token quality weights based on correlations with multimodal template tokens.
    • Introduced a Prompt-based Spatio-temporal Encoder Module (PSEM) to effectively utilize spatio-temporal multimodal information while mitigating low-quality feature impacts.

    Related Experiment Videos

    Last Updated: Jan 10, 2026

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
    04:23

    A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

    Published on: April 21, 2023

    2.3K

    Main Results:

    • The proposed QSTNet demonstrates superior performance on four RGBT benchmark datasets.
    • The QTWM effectively suppresses the negative effects of low-quality tokens in spatio-temporal feature representations.

    Conclusions:

    • QSTNet offers a robust solution for RGBT tracking by intelligently handling token quality.
    • The method significantly outperforms existing state-of-the-art RGBT tracking techniques.