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 18, 2026

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

9.6K

Unsupervised Visible-Infrared ReID via Pseudo-Label Correction and Modality-Level Alignment.

Yexin Liu, Weiming Zhang, Athanasios V Vasilakos

    IEEE Transactions on Neural Networks and Learning Systems
    |September 9, 2025
    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

    HiRMD: A System for Mortality Prediction via LLM-Based High-Risk Information Extraction and Diagnosis.

    IEEE transactions on bio-medical engineering·2026
    Same author

    Memristive Physical Reservoir Computing.

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

    Advancing Chinese Conversation-based Patient Guidance with a Benchmark and Knowledge-Evolvable Assistant.

    IEEE journal of biomedical and health informatics·2025
    Same author

    Optimized Tri-Coil Magnetic Guidance of Nanorobots for Targeted Plaque Therapy in the Middle Cerebral Artery.

    IEEE transactions on nanobioscience·2025
    Same author

    BianCang: A Traditional Chinese Medicine Large Language Model.

    IEEE journal of biomedical and health informatics·2025
    Same author

    Real-Time Detection of Myocardial Infarction Onset Using Communication Network-Enabled Recursive Bayesian Updating.

    IEEE transactions on nanobioscience·2025
    Same journal

    Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    cPU: Consistent Risk Estimator for Positive-Unlabeled Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Tuning-Free Latent Diffusion Models for Ultrahigh-Resolution Image Editing.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

    IEEE transactions on neural networks and learning systems·2026
    See all related articles

    This study introduces a new framework for unsupervised visible-infrared person reidentification (UVI-ReID), improving accuracy by correcting noisy labels and aligning cross-modality features. The PRAISE method enhances human detection in diverse environments without manual labeling.

    Area of Science:

    • Computer Vision
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Unsupervised visible-infrared person reidentification (UVI-ReID) is crucial for human detection across different environments without requiring labeled data.
    • Existing UVI-ReID methods face challenges with noisy pseudo-labels from clustering and potential misalignment of features across visible and infrared modalities.
    • Theoretical analysis introduced an interpretable generalization upper bound to guide the development of improved UVI-ReID frameworks.

    Purpose of the Study:

    • To propose a novel unsupervised cross-modality person reidentification framework (PRAISE) addressing key challenges in UVI-ReID.
    • To enhance the accuracy and robustness of person reidentification systems using both visible and infrared imagery.
    • To reduce the modality gap and learn identity-discriminative, modality-invariant features.

    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

    1.0K

    Related Experiment Videos

    Last Updated: Jan 18, 2026

    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

    9.6K
    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

    1.0K

    Main Methods:

    • Developed a pseudo-label correction (PLC) strategy using a beta mixture model (BMM) to rectify misclustered labels and a perceptual term in contrastive learning.
    • Introduced a modality-level alignment (MLA) strategy to generate paired visible-infrared latent features and align their labeling functions.
    • Implemented a novel unsupervised cross-modality person reidentification framework (PRAISE).

    Main Results:

    • The proposed PRAISE framework achieved state-of-the-art (SOTA) performance on two benchmark datasets for unsupervised visible-ReID.
    • The PLC strategy effectively mitigated issues arising from noisy pseudo-labels in the clustering process.
    • The MLA strategy successfully reduced the modality gap, leading to more discriminative and invariant features.

    Conclusions:

    • The PRAISE framework offers a significant advancement in unsupervised visible-infrared person reidentification.
    • The combination of PLC and MLA strategies effectively addresses the limitations of previous UVI-ReID methods.
    • This research contributes to more robust and accurate human detection systems in complex, multi-modal environments.