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 23, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

Context-aware reliability exploration for unsupervised domain adaptive person re-identification.

Jialu Liu1, Xing Tan1, Meng Yang1

  • 1School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China; Pengcheng Laboratory, China.

Neural Networks : the Official Journal of the International Neural Network Society
|June 20, 2026
PubMed
Summary

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

Urinary ANGPTL3: a novel noninvasive biomarker for podocyte injury in pediatric glomerular diseases.

Journal of translational medicine·2026
Same author

Interpretable machine learning model for predicting kidney failure among CAKUT children in multicenter large-scale study.

NPJ digital medicine·2026
Same author

Halogen-Doped Hydrothermal Carbonation Carbon Photocatalytic Activation of Persulfate for Thiamethoxam Degradation: Halogen Doping Enhances Light Absorption.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

NeuroLangSeg: Language-Guided Subcortical Segmentation with Pseudo-Supervision and Anatomical-Linguistic Validation.

Proceedings of machine learning research·2026
Same author

Decoding the Oxygen Reduction Reaction: Mechanistic Insights from Transition Metal Heterostructures.

Nano-micro letters·2026
Same author

Comparative Study on the Hydration, Mechanical Properties, and Energy Storage Performance of MPC-Based Solid Electrolytes Modified by Different Ionic PAMs.

Materials (Basel, Switzerland)·2026

This study introduces a Context-Aware Reliability Exploration (CARE) framework to improve unsupervised domain adaptive person re-identification (ReID). CARE reduces pseudo-label noise by refining target-domain labels and leveraging source-domain knowledge for better feature learning.

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to bridge the gap between labeled source and unlabeled target domains.
  • Existing methods often struggle with noisy pseudo-labels, limiting performance in ReID tasks.
  • The challenge is exacerbated by visually similar samples from different identities, leading to label noise.

Purpose of the Study:

  • To propose a novel Context-Aware Reliability Exploration (CARE) framework for UDA person ReID.
  • To mitigate the impact of pseudo-label noise in the target domain.
  • To enhance knowledge transfer from the source to the target domain.

Main Methods:

  • A neighbor-based reliable supervision selection strategy to identify high-quality pseudo-labels.
Keywords:
Person re-identificationPseudo-label optimizationUnsupervised domain adaptation

Related Experiment Videos

Last Updated: Jun 23, 2026

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis
05:48

Memorization-Based Training and Testing Paradigm for Robust Vocal Identity Recognition in Expressive Speech Using Event-Related Potentials Analysis

Published on: August 9, 2024

  • Consistency learning applied to samples with unreliable labels for self-supervised feature extraction.
  • A dynamic knowledge transfer module that minimizes inter-domain distance based on domain proximity.

    • Main Results:

    • The CARE framework significantly reduces label noise in target domain pseudo-labels.
    • Improved discriminative feature representation learning for person ReID.
    • Outperforms existing state-of-the-art methods on unsupervised domain adaptive person ReID benchmarks.

    Conclusions:

    • The proposed CARE framework effectively addresses pseudo-label noise in UDA person ReID.
    • Achieves superior performance by refining pseudo-labels and enhancing cross-domain knowledge transfer.
    • Demonstrates a promising direction for future research in domain adaptive ReID.