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 4, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

279

Deep Reconstruction Models for Image Set Classification.

Munawar Hayat, Mohammed Bennamoun, Senjian An

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |September 10, 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

    Triple Spectral Fusion for Sensor-based Human Activity Recognition.

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

    DynaPURLS: Dynamic Refinement of Part-Aware Representations for Skeleton-Based Zero-Shot Action Recognition.

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

    Fully automated, deep learning, cardiac CT-based multimodal network for cardiovascular risk stratification in high-risk perioperative patients.

    European heart journal. Digital health·2026
    Same author

    Trait Association for Flowering Time in Lentil from Global Multi-Environment Data Using GWAS and Machine Learning.

    Plants (Basel, Switzerland)·2026
    Same author

    AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis.

    IEEE transactions on neural networks and learning systems·2026
    Same author

    Unleashing the Power of Text-to-Image Diffusion Models for Category-Agnostic Pose Estimation.

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

    Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

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

    RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

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

    CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

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

    DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

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

    Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

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

    Learning Shape Anchors for Holistic Indoor Scene Understanding.

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

    This study introduces a novel deep learning framework for image set classification that discovers underlying geometric structures without prior assumptions. The method, Template Deep Reconstruction Model (TDRM), outperforms existing approaches in face and object recognition tasks.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Image set classification is crucial for real-world applications like surveillance and personal photo organization.
    • Existing methods often rely on assumptions about geometric structures within image sets, limiting their applicability.
    • Deep learning offers promising avenues for more robust image set classification.

    Purpose of the Study:

    • To develop a deep learning framework for image set classification that does not require prior geometric assumptions.
    • To automatically discover the underlying geometric structure within image sets.
    • To improve the performance of face and object recognition from image sets.

    Main Methods:

    • Introduced a Template Deep Reconstruction Model (TDRM) framework.

    Related Experiment Videos

    Last Updated: Apr 4, 2026

    Automated Joint Space Detection Improves Bone Segmentation Accuracy
    06:45

    Automated Joint Space Detection Improves Bone Segmentation Accuracy

    Published on: November 28, 2025

    279
  • Utilized unsupervised pre-training with Gaussian Restricted Boltzmann Machines (GRBMs) for parameter initialization.
  • Trained class-specific Deep Reconstruction Models (DRMs) and employed voting strategies based on reconstruction errors for classification.

    • Main Results:

    • The proposed TDRM framework demonstrated efficacy in face and object recognition from image sets.
    • Experimental results showed consistent outperformance compared to existing state-of-the-art methods.
    • The method successfully discovered underlying geometric structures without explicit prior assumptions.

    Conclusions:

    • The developed deep learning framework offers a flexible and effective approach to image set classification.
    • The TDRM method advances the state of the art by eliminating the need for predefined geometric assumptions.
    • This framework has significant potential for various real-world image analysis applications.