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

Structural Classification of Joints01:20

Structural Classification of Joints

3.9K
Joints, also known as articulations, are classified based on their structural characteristics, i.e., based on whether the articulating surfaces of the adjacent bones are directly connected by fibrous connective tissue or cartilage, or whether the articulating surfaces contact each other within a fluid-filled joint cavity. These differences serve to divide the joints of the body into three structural classifications.
A fibrous joint is where the adjacent bones are united by fibrous connective...
3.9K
Ranks01:02

Ranks

285
Unlike parametric methods, nonparametric statistics are ideal for nominal and ordinal data, requiring fewer assumptions about the population's nature or distribution. This makes nonparametric methods easier to apply and interpret, as they do not depend on parameters like mean or standard deviation. One common approach in nonparametric analysis is to sort data according to a specific criterion. For instance, we might arrange weather data from hottest to coldest days in a month or rank cities...
285
Estimation of the Physical Quantities01:05

Estimation of the Physical Quantities

5.3K
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...
5.3K
Functional Classification of Joints01:09

Functional Classification of Joints

4.5K
Functional Classification of Joints
The functional classification of joints is determined by the amount of mobility between the adjacent bones. Joints are functionally classified as a synarthrosis or immobile joint, an amphiarthrosis or slightly moveable joint, or as a diarthrosis, a freely moveable joint. Fibrous and cartilaginous joints can be functionally classified as either synarthroses  or amphiarthroses, whereas all synovial joints are classified as diarthroses.
Synarthrosis
An...
4.5K

You might also read

Related Articles

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

Sort by
Same author

Vertical stratification and distribution patterns of the ARG resistome in Fuxian Lake: Insights from a global baseline.

Journal of hazardous materials·2026
Same author

High-Performance Photochromic Diarylethene with a Boron-Nitrogen Heterocyclic Ethene Bridge.

Molecules (Basel, Switzerland)·2026
Same author

The role of radiomics in predicting the response to neoadjuvant chemotherapy for breast cancer.

Cancer biology & medicine·2026
Same author

High Electron Mobility in Ge Films Grown on Si (001) by an 8-Inch Molecular Beam Epitaxy System.

Nanomaterials (Basel, Switzerland)·2026
Same author

Contrasting impacts of pretransplant cytoreduction and post-transplant maintenance on outcomes of allogeneic haematopoietic stem cell transplantation in myelodysplastic syndromes: Real-world multicentre evidence.

British journal of haematology·2026
Same author

Multimetric analysis uncovers time-dependent climate forcings from China's 2.3-fold cropland reactive nitrogen emissions.

Proceedings of the National Academy of Sciences of the United States of America·2026

Related Experiment Video

Updated: Sep 5, 2025

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.7K

An Improved Mixture Density Network for 3D Human Pose Estimation with Ordinal Ranking.

Yiqi Wu1,2, Shichao Ma1, Dejun Zhang1,2

  • 1School of Computer Science, China University of Geosciences, Wuhan 430074, China.

Sensors (Basel, Switzerland)
|July 9, 2022
PubMed
Summary

Estimating 3D human poses from 2D images is challenging. The Locally Connected Mixture Density Network (LCMDN) predicts multiple pose hypotheses, improving accuracy and robustness for 3D pose estimation.

Keywords:
3D human pose estimationGaussian mixture modelgraphic convolutional networkmixture density networkordinal ranking

More Related Videos

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.8K
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.3K

Related Experiment Videos

Last Updated: Sep 5, 2025

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.7K
3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

10.8K
Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

10.3K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Human Pose Estimation

Background:

  • Estimating accurate 3D human poses from 2D images is difficult due to missing depth information.
  • Existing methods often rely on direct regression or unimodal estimates, limiting their accuracy.

Purpose of the Study:

  • To propose an improved Mixture Density Network (MDN) for 3D human pose estimation, named the Locally Connected Mixture Density Network (LCMDN).
  • To enhance the representation capability and robustness of existing 3D pose estimation techniques.

Main Methods:

  • The LCMDN estimates 2D joint points first, then extracts human joint correlations using a feature extractor.
  • It employs a Locally Connected Network (LCN) instead of a Fully Connected Network (FCN) for feature extraction to better utilize joint relationships.
  • Multiple pose hypotheses are generated and scored using a 3D pose selector based on ordinal joint ranking.

Main Results:

  • The LCMDN achieves an average Mean Per Joint Position Error (MPJPE) of 50 mm on the Human3.6M dataset.
  • Performance is on par with or better than current state-of-the-art methods.
  • Qualitative results on the MPII dataset demonstrate strong generalization ability.

Conclusions:

  • The proposed LCMDN significantly improves 3D human pose estimation accuracy and robustness.
  • The integration of LCN and MDN offers a promising approach for handling the inherent ambiguities in 2D to 3D pose estimation.
  • The method shows potential for real-world applications requiring accurate human pose understanding.