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

Hybrid Deep Learning for Face Verification.

Yi Sun, Xiaogang Wang, Xiaoou Tang

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |December 15, 2015
    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

    Association between erectile dysfunction and the predicted 10-year risk for atherosclerosis cardiovascular disease among U.S. men: a population-based study from the NHANES 2001-2004.

    Frontiers in endocrinology·2025
    Same author

    FOXF1 promotes ovarian cancer metastasis by facilitating HMGA2-mediated USP30-dependent S100A6 deubiquitination.

    Biochimica et biophysica acta. Molecular basis of disease·2024
    Same author

    Quinazolinone-to-Isoquinoline Metamorphosis by Ruthenium-Catalyzed [4+2] Annulation with Sulfoxonium Ylides.

    Organic letters·2024
    Same author

    Synthesis of Functionalized Indoles by an Iridium-Catalyzed N-H Insertion Cascade: Nucleophilic Cyclization of Naphthylamines with α-Diazocarbonyl Compounds.

    The Journal of organic chemistry·2024
    Same author

    CLIP170 enhancing FOSL1 expression via attenuating ubiquitin-mediated degradation of β-catenin drives renal cell carcinoma progression.

    Cellular and molecular life sciences : CMLS·2024
    Same author

    Derangetropy in Probability Distributions and Information Dynamics.

    Entropy (Basel, Switzerland)·2024
    Same journal

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

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

    Learning Topology-Aware Representations via Test-Time Adaptation for Anomaly Segmentation.

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

    TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

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

    SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

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

    HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

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

    Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

    IEEE transactions on pattern analysis and machine intelligence·2026
    See all related articles

    This study introduces a hybrid convolutional network (ConvNet)-Restricted Boltzmann Machine (RBM) model for advanced face verification. The novel approach learns high-level relational visual features, achieving state-of-the-art results on the LFW dataset.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Face verification is a critical biometric identification task.
    • Existing methods often struggle with subtle identity variations and diverse image conditions.
    • Learning discriminative visual features is essential for robust face verification.

    Purpose of the Study:

    • To propose a novel hybrid deep learning model for enhanced face verification.
    • To learn high-level relational visual features capturing identity similarity.
    • To achieve state-of-the-art performance on challenging face verification benchmarks.

    Main Methods:

    • A hybrid model combining deep Convolutional Neural Networks (ConvNets) and Restricted Boltzmann Machines (RBMs).
    • ConvNets extract local and global relational visual features from face image pairs.

    Related Experiment Videos

  • Features from the last hidden layer of ConvNets are concatenated and classified by an RBM.
  • Joint optimization of the entire hybrid network after separate pre-training.

    • Main Results:

    • The proposed hybrid ConvNet-RBM model achieves state-of-the-art face verification performance.
    • Superior results are demonstrated on the challenging Labeled Faces in the Wild (LFW) dataset.
    • The model shows effectiveness under both unrestricted and external data training protocols.

    Conclusions:

    • The hybrid ConvNet-RBM model effectively learns rich identity similarity information.
    • Relational visual features extracted by deep ConvNets are highly discriminative for face verification.
    • The proposed approach offers a promising direction for advancing face recognition technologies.