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

Sign Test for Matched Pairs01:17

Sign Test for Matched Pairs

417
The sign test for matched pairs offers a robust method for comparing two paired samples, often for the effects of an intervention in one of them. This method is very useful in situations where the underlying distribution of the data is unknown. The test compares two related samples—often pre- and post-treatment measurements on the same subjects—to determine if there are significant differences in their median values.
To conduct the sign test, we first calculate the differences in...
417
Structural Joints: Synovial Joints01:16

Structural Joints: Synovial Joints

7.0K
Synovial joints are the most common type of joint in the body. A key structural characteristic for a synovial joint is the presence of a joint cavity. This fluid-filled space is where the articulating surfaces of the bones contact each other. Also, unlike fibrous or cartilaginous joints, the articulating bone surfaces at a synovial joint are not directly connected to each other with fibrous connective tissue or cartilage. This gives the bones of a synovial joint the ability to move smoothly...
7.0K
Structural Joints: Fibrous Joints01:03

Structural Joints: Fibrous Joints

3.8K
Fibrous joints are a type of joint where the bones are connected by fibrous connective tissue. These joints provide stability and minimal to no movement between the articulating bones. There are three types of fibrous joints.
Suture
All the bones of the skull, except for the mandible, are joined to each other by a fibrous joint called a suture. The fibrous connective tissue found at a suture strongly unites the adjacent skull bones and thus helps to protect the brain and form the face. In...
3.8K
Structural Joints: Cartilaginous Joints01:17

Structural Joints: Cartilaginous Joints

4.1K
As the name indicates, at a cartilaginous joint, the adjacent bones are united by cartilage, a tough but flexible type of connective tissue. Unlike synovial joints, these types of joints lack a joint cavity and involve bones joined together by either hyaline cartilage or fibrocartilage.
There are two types of cartilaginous joints:
Synchondrosis
A synchondrosis ("joined by cartilage") is a cartilaginous joint where bones are connected by hyaline cartilage. Synchondrosis may be temporary...
4.1K
Joints01:26

Joints

35.8K
Joints, also called articulations or articular surfaces, are points at which ligaments or other tissues connect adjacent bones. Joints permit movement and stability, and can be classified based on their structure or function.
Structural joint classifications are based on the material that makes up the joint as well as whether or not the joint contains a space between the bones. Joints are structurally classified as fibrous, cartilaginous, or synovial.
Fibrous Joints Are Immovable
The bones of a...
35.8K
Moment of Inertia01:14

Moment of Inertia

19.6K
The comparability between linear and angular velocities, linear and angular accelerations, and the kinematic equations of translational and rotational motion can be extended to the concept of inertia.
If a rigid body is rotating about an axis but is not in translational motion, its translational kinetic energy is zero. However, since each particle undergoes rotational motion, it possesses non-zero velocity and kinetic energy. Thus, the kinetic energy of the rigid body, which is the sum of the...
19.6K

You might also read

Related Articles

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

Sort by
Same author

A Modularized Higher-Order Diagnostic Classification Model for Clustered Attribute Hierarchies.

Multivariate behavioral research·2026
Same author

Uncovering Hierarchical Asymmetries in Artificial Intelligence Transformation: Navigating the Bright and Dark Sides Across Organizational Levels.

Journal of visualized experiments : JoVE·2026
Same author

Effects of divalent cations on diffusion dynamics of biological water confined between lipid membranes.

The Journal of chemical physics·2026
Same author

Neural Network Copulas for Generating Synthetic Test Data Preserving Psychometric Properties.

Journal of Intelligence·2026
Same author

Composite marginal likelihood estimation of higher-order diagnostic classification models under high dimensionality.

The British journal of mathematical and statistical psychology·2026
Same author

A Landmark-Guided Dual-Stream Synergistic Framework for Automated Intracranial Aneurysm Detection in Magnetic Resonance Angiography.

Journal of imaging informatics in medicine·2026

Related Experiment Video

Updated: Feb 7, 2026

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.2K

Joint moment-matching autoencoders.

Mohammad Ahangar Kiasari1, Dennis Singh Moirangthem1, Minho Lee1

  • 1School of Electronics Engineering, IT1, Kyungpook National University, 80 Daehakro, Bukgu, Daegu 41566, South Korea.

Neural Networks : the Official Journal of the International Neural Network Society
|August 4, 2018
PubMed
Summary
This summary is machine-generated.

This study introduces joint moment-matching autoencoders (JMA) for image transformation across multiple domains without paired data. The JMA model efficiently performs cross-domain image translation using perceptual loss and maximum mean discrepancy.

Keywords:
Generative modelsImage transformationMoment matchingMultiple domain transformation

More Related Videos

Creation of a Knee Joint-on-a-Chip for Modeling Joint Diseases and Testing Drugs
12:44

Creation of a Knee Joint-on-a-Chip for Modeling Joint Diseases and Testing Drugs

Published on: January 27, 2023

4.5K
Tissue Collection and RNA Extraction from the Human Osteoarthritic Knee Joint
06:06

Tissue Collection and RNA Extraction from the Human Osteoarthritic Knee Joint

Published on: July 22, 2021

6.9K

Related Experiment Videos

Last Updated: Feb 7, 2026

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers
12:39

A Methodology for Capturing Joint Visual Attention Using Mobile Eye-Trackers

Published on: January 18, 2020

8.2K
Creation of a Knee Joint-on-a-Chip for Modeling Joint Diseases and Testing Drugs
12:44

Creation of a Knee Joint-on-a-Chip for Modeling Joint Diseases and Testing Drugs

Published on: January 27, 2023

4.5K
Tissue Collection and RNA Extraction from the Human Osteoarthritic Knee Joint
06:06

Tissue Collection and RNA Extraction from the Human Osteoarthritic Knee Joint

Published on: July 22, 2021

6.9K

Area of Science:

  • Computer Vision
  • Deep Learning
  • Generative Models

Background:

  • Image transformation between different domains is a complex challenge in deep generative networks.
  • Acquiring paired images across domains is often impractical and costly for real-world applications.

Purpose of the Study:

  • To propose a novel model for unsupervised cross-domain image transformation.
  • To enable effective image translation between multiple domains without relying on paired data.

Main Methods:

  • Introduced the joint moment-matching autoencoders (JMA) framework.
  • Utilized perceptual loss and maximum mean discrepancy criteria for learning transformations.
  • Operated without requiring paired images between the source and target domains.

Main Results:

  • The JMA framework successfully learned to transform images between multiple domains without paired data.
  • Demonstrated strong performance in both generative tasks and domain transformation.
  • Achieved better computational efficiency compared to conventional methods.

Conclusions:

  • The proposed JMA model offers an effective solution for unsupervised cross-domain image transformation.
  • JMA provides a computationally efficient and high-performing alternative for multi-domain image translation.