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: Apr 27, 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

526

Person re-identification over camera networks using multi-task distance metric learning.

Lianyang Ma, Xiaokang Yang, Dacheng Tao

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |June 24, 2014
    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

    Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.

    IEEE transactions on pattern analysis and machine intelligence·2026
    Same author

    Holistic Invariant Retracing for Distortion-Resilient Multi-Modal Learning in Spatial Transcriptomics.

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

    Demonstration of efficient predictive surrogates for large-scale quantum processors.

    Nature communications·2026
    Same author

    A DeepSeek-powered AI system for automated chest radiograph interpretation in clinical practice.

    Nature communications·2026
    Same author

    NoisePO: Efficient Semantic Noise Generation and Ranking for Diffusion-Based Text-to-Image Synthesis.

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

    Stability and Generalization for Distributed SGDA.

    IEEE transactions on pattern analysis and machine intelligence·2026

    This study introduces a new multitask learning approach for person reidentification across camera networks. The novel multitask maximally collapsing metric learning (MtMCML) model significantly improves reidentification accuracy despite varying camera conditions.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Pattern Recognition

    Background:

    • Person reidentification across camera networks is challenging due to varying camera settings and environmental conditions.
    • Existing common Mahalanobis distance metric methods struggle with camera differences and are prone to overfitting with limited data.
    • Manual labeling for person reidentification datasets is time-consuming and labor-intensive.

    Purpose of the Study:

    • To address the limitations of current person reidentification methods in camera networks.
    • To develop a robust approach that accounts for differences in camera settings and environmental variability.
    • To improve the accuracy and efficiency of person reidentification in complex surveillance scenarios.

    Main Methods:

    • Reformulating person reidentification as a multitask distance metric learning problem.

    Related Experiment Videos

    Last Updated: Apr 27, 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

    526
  • Designing multiple related Mahalanobis distance metrics to handle camera network complexities.
  • Introducing a novel multitask maximally collapsing metric learning (MtMCML) model with joint regularization to prevent overfitting.

    • Main Results:

    • The proposed multitask learning framework improves person reidentification performance.
    • The MtMCML model demonstrates substantial performance gains over existing state-of-the-art methods.
    • The approach effectively handles variability in illumination, camera angles, and background clutter.

    Conclusions:

    • Formulating person reidentification in camera networks as a multitask learning problem enhances performance.
    • The novel MtMCML model offers a significant advancement in person reidentification accuracy and robustness.
    • This work provides a more effective solution for surveillance and security applications.