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 Videos

Transfer learning of structured representation for face recognition.

Chuan-Xian Ren, Dao-Qing Dai, Ke-Kun Huang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |November 1, 2014
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Association Areas of the Cortex01:21

    Association Areas of the Cortex

    10.1K
    Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
    Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
    10.1K

    You might also read

    Related Articles

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

    Sort by
    Same author

    Open-Set Domain Adaptation via Target-Relaxed Optimal Transport.

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

    CGDock: Curvature-Aware Geometric Flow Framework for Protein-Ligand Docking.

    Journal of chemical information and modeling·2026
    Same author

    Local and High-Order Consistency Coding and Adaptation for Cross-Hypergraph Node Classification.

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

    Partial Domain Adaptation via Importance Sampling-Based Shift Correction.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025
    Same author

    When Invariant Representation Learning Meets Label Shift: Insufficiency and Theoretical Insights.

    IEEE transactions on pattern analysis and machine intelligence·2024
    Same author

    Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation.

    IEEE transactions on pattern analysis and machine intelligence·2024

    This study introduces a novel transferrable representation learning model for robust face recognition. The approach enhances generalization across diverse datasets by effectively leveraging discriminant information from both source and target domains.

    Area of Science:

    • Computer Vision
    • Image Processing
    • Machine Learning

    Background:

    • Face recognition remains challenging under uncontrolled conditions like complex backgrounds and variable resolutions.
    • Existing methods often lack generality across different datasets, performing poorly when transferred.
    • Source domain properties significantly influence classification outcomes in face recognition tasks.

    Purpose of the Study:

    • To propose a transferrable representation learning model for enhanced face recognition performance.
    • To improve the generality and robustness of face recognition systems across diverse datasets.
    • To exploit discriminant information from multiple domains for better feature representation.

    Main Methods:

    • A bioinspired face representation is modeled as structured and approximately stable characterization.

    Related Experiment Videos

  • The model exploits commonalities between source and target domains for transfer learning.
  • A grouped boost of features highlights and shares discriminant orientations and scales.

    • Main Results:

    • The proposed method demonstrates improved face recognition performance on benchmark datasets.
    • Experiments on uncontrolled datasets like FRGC v2.0 and LFW show the algorithm's efficacy.
    • The transfer learning approach enhances generalization capabilities.

    Conclusions:

    • The developed transferrable representation learning model effectively addresses challenges in uncontrolled face recognition.
    • The framework offers flexibility for integrating various feature operators and classification metrics.
    • The method shows potential for broader applications including low-resolution face recognition and object detection.