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
  1. Home
  3. Enhancing Unsupervised Multi-source Domain Adaptation For Person Re-identification Via Mixture Of Experts And Graph-based Relation.
  1. Home
  3. Enhancing Unsupervised Multi-source Domain Adaptation For Person Re-identification Via Mixture Of Experts And Graph-based Relation.

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

Model-Informed Speech Enhancement Using Virtual Room Acoustics and Acoustic Descriptor Optimization.

Sensors (Basel, Switzerland)·2026
Same author

EnzRetro: Enzymatic Retrosynthetic Planning With Site-Specific Reaction Edits Based on Sequence Generative Architecture.

Exploration (Beijing, China)·2026
Same author

Real-Time Signal Processing for Distributed Acoustic Sensing and Acoustic Sensing Systems Under Non-Stationary Noise.

Sensors (Basel, Switzerland)·2026
Same author

A Novel Metabolic Pathway Design Method Based on Evolutionary Algorithms and Metabolic Network Evaluation.

Journal of chemical information and modeling·2026
Same author

Molecular Property Prediction Based on Improved Graph Transformer Network and Multitask Joint Learning Strategy.

Journal of chemical information and modeling·2025
Same author

A Unified Deep Learning Ensemble Framework for Voice-Based Parkinson's Disease Detection and Motor Severity Prediction.

Bioengineering (Basel, Switzerland)·2025
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
Same journal

Three-Dimensional Modeling and Performance Analysis of Dynamic mmWave V2I Networks Based on Stochastic Geometry.

Sensors (Basel, Switzerland)·2026
Same journal

Personalization of Caffeine Therapy for Apnea of Prematurity: A Potential Role for Sensor Technologies?

Sensors (Basel, Switzerland)·2026
See all related articles

Related Experiment Videos

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and

Hao Li1,2, Yuyang Feng1, Xin Zhao1

  • 1School of Electrical and Information Engineering, Tianjin University, Tianjin 300072, China.

Sensors (Basel, Switzerland)
|June 26, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces a new framework for person re-identification (re-ID) using a Mixture of Experts feature extraction network and a Graph-Based Relation module. The approach enhances cross-camera matching by balancing domain-invariant features and domain-specific styles for improved performance.

Keywords:
Mixture of Expertsadjacency matrixdomain-specific style informationperson re-identification

Related Experiment Videos

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Person re-identification (re-ID) is crucial for matching individuals across different camera views.
  • Current multi-source unsupervised domain adaptation (UDA) re-ID methods struggle with balancing domain-invariant features and domain-specific styles.
  • Existing methods also fail to adequately model correlations among diverse source domains, limiting cross-domain generalization.

Purpose of the Study:

  • To propose a novel multi-source UDA re-ID framework addressing limitations in feature learning and domain correlation modeling.
  • To enhance the effectiveness of person re-identification across disjoint camera views.

Main Methods:

  • A Mixture of Experts feature extraction (MEFE) network with mixed Instance and Batch Normalization (MIBN) for robust domain-invariant features.
  • An embedded domain-specific style information (DSI) module to preserve style details.
  • A Graph-Based Relation (GBR) module with cascaded Graph Attention and Graph Convolution Networks (GATs/GCNs) for multi-source feature fusion.
  • Center maximum mean discrepancy loss to minimize cross-domain distribution discrepancies.

Main Results:

  • The proposed framework achieves state-of-the-art performance in multi-source unsupervised domain adaptation for person re-identification.
  • Demonstrated substantial improvements over mainstream UDA re-ID approaches on large-scale datasets.
  • Successfully balanced domain-invariant feature learning and domain-specific style preservation.

Conclusions:

  • The novel MEFE network and GBR module effectively address key challenges in multi-source UDA re-ID.
  • The proposed method offers superior cross-domain generalization capabilities.
  • This framework represents a significant advancement in person re-identification technology.