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 Concept Videos

Classification of Signals01:30

Classification of Signals

975
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
975
Classification of Systems-II01:31

Classification of Systems-II

249
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
249

You might also read

Related Articles

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

Sort by
Same author

Paving the Way for Point Cloud Video Representation Learning Using a PDE Model.

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

EvaNet: Toward More Efficient and Consistent Infrared and Visible Image Fusion Assessment.

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

Affine non-negative collaborative representation based pattern classification.

Complex & intelligent systems·2026
Same author

Interactive image-to-video transfer learning.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

Probabilistically Aligned View-Unaligned Clustering With Adaptive Template Selection.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

RefineFuse: an end-to-end network for multi-scale refinement fusion of multi-modality images.

Visual intelligence·2025

Related Experiment Video

Updated: Sep 27, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

537

Learning a discriminative SPD manifold neural network for image set classification.

Rui Wang1, Xiao-Jun Wu1, Ziheng Chen1

  • 1School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China; Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence, Jiangnan University, Wuxi 214122, China.

Neural Networks : the Official Journal of the International Neural Network Society
|April 11, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces novel Riemannian operations for symmetric positive definite (SPD) manifold neural networks. These methods enhance invariant representation learning for improved performance in tasks like image set classification.

Keywords:
Image set classificationMetric learningRiemannian barycenterRiemannian optimizationSPD manifold neural network

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

662
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

911

Related Experiment Videos

Last Updated: Sep 27, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

537
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

662
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

911

Area of Science:

  • Computer Vision
  • Machine Learning
  • Differential Geometry

Background:

  • Pattern analysis on Symmetric Positive Definite (SPD) manifolds presents challenges due to non-Euclidean data properties.
  • Existing neural network architectures struggle with diverse data appearance, hindering invariant representation learning.

Purpose of the Study:

  • To develop novel Riemannian operation modules for SPD manifold neural networks.
  • To improve invariant representation learning for enhanced performance in SPD data analysis.

Main Methods:

  • Proposed two Riemannian operation modules: a Riemannian batch regularization (RBR) layer and a Riemannian pooling operation.
  • Incorporated metric learning regularization and geometric computations (Riemannian barycenter, optimization) on manifolds.

Main Results:

  • The proposed RBR layer facilitates discriminative manifold-to-manifold transformation networks.
  • The Riemannian pooling operation enhances geometric feature extraction on SPD manifolds.
  • Demonstrated efficacy across five benchmark datasets.

Conclusions:

  • The developed Riemannian modules effectively address challenges in SPD manifold learning.
  • The approach yields improved invariant representations for SPD data analysis.
  • The methods show significant potential for applications like image set classification.