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

Muscle Coordination and Action01:24

Muscle Coordination and Action

2.4K
Muscle coordination is a complex and finely tuned process essential for smooth and purposeful movements like flexion, extension, adduction, abduction, and rotation. The human body orchestrates the actions of various muscles working in concert, each with a specific role. Four functional types describe how muscles work together: agonist, antagonist, synergist, and fixator.
Agonists
Agonist muscles, often called prime movers, are the primary muscles responsible for producing a specific movement....
2.4K

You might also read

Related Articles

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

Sort by
Same author

Visual-Text Reference Pretraining Model for Image Captioning.

Computational intelligence and neuroscience·2022
Same author

Multiscale Aggregate Networks with Dense Connections for Crowd Counting.

Computational intelligence and neuroscience·2021
Same author

[Expression Level and Clinical Significance of Gli1 in Patients with Myelodysplastic Syndrome].

Zhongguo shi yan xue ye xue za zhi·2019
Same author

Overexpression of EPAC2 reduces the invasion of glioma cells via MMP-2.

Oncology letters·2019
Same author

Microcystin-LR-regulated transcriptome dynamics in ZFL cells.

Aquatic toxicology (Amsterdam, Netherlands)·2019
Same author

Endocannabinoid contributions to alcohol habits and motivation: Relevance to treatment.

Addiction biology·2019
Same journal

RETRACTION: Real-Time Modulation of Physical Training Intensity Based on Wavelet Recursive Fuzzy Neural Networks.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Multidimensional Heterogeneous Network Link Adaptation Based on Mobile Environment.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Framework to Segment and Evaluate Multiple Sclerosis Lesion in MRI Slices Using VGG-UNet.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Facial Emotion Recognition Using a Novel Fusion of Convolutional Neural Network and Local Binary Pattern in Crime Investigation.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Automatic Intelligent System Using Medical of Things for Multiple Sclerosis Detection.

Computational intelligence and neuroscience·2026
Same journal

RETRACTION: Intangible Cultural Heritage Reproduction and Revitalization: Value Feedback, Practice, and Exploration Based on the IPA Model.

Computational intelligence and neuroscience·2026
See all related articles

Related Experiment Video

Updated: Oct 22, 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

1.8K

Skeleton-Based Action Recognition Based on Distance Vector and Multihigh View Adaptive Networks.

Min Zhang1, Haijie Yang1, Pengfei Li1

  • 1School of Computer Science, Hangzhou Dianzi University, Hangzhou 310000, China.

Computational Intelligence and Neuroscience
|August 30, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a novel action recognition method using distance vectors and multi-high view adaptive networks to capture implicit joint correlations and improve robustness across different views. The DV-MHNet model enhances human action recognition accuracy.

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

708

Related Experiment Videos

Last Updated: Oct 22, 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

1.8K
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

708

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Skeleton-based human action recognition faces challenges with fixed graph structures, limiting capture of implicit joint correlations.
  • Varying viewpoints and occluded keypoints in human action recognition lead to significant recognition errors.
  • Existing methods often fail to capture global relationships and adapt to diverse observational perspectives.

Purpose of the Study:

  • To propose a novel action recognition method, the Distance Vector and Multi-High View Adaptive Network (DV-MHNet), addressing limitations of fixed skeleton graphs and view variations.
  • To enhance the robustness and generalization of human action recognition models by incorporating multi-high view adaptivity and global relationship modeling.
  • To improve the accuracy of skeleton-based human action recognition by capturing both local and global dependencies and handling viewpoint variations.

Main Methods:

  • Developed Multi-High (MH) view adaptive networks to automatically select optimal observation views and ensure complete keypoint information.
  • Introduced a Distance Vector (DV) mechanism to establish relative distances and orientations between keypoints across frames, capturing global relationships.
  • Constructed a spatial-temporal graph convolutional network integrating spatial and temporal information for effective action feature learning.

Main Results:

  • Ablation studies demonstrated the effectiveness of the multi-high view adaptive networks and the distance vector mechanism.
  • The proposed DV-MHNet model achieved superior performance compared to traditional spatial-temporal graph convolutional networks.
  • The method showed enhanced robustness and generalization capabilities in human action recognition tasks.

Conclusions:

  • The DV-MHNet model effectively addresses limitations in skeleton-based action recognition by integrating multi-view adaptivity and global relationship modeling.
  • The proposed approach significantly improves recognition accuracy and robustness across different viewpoints and datasets.
  • This work offers a promising direction for advancing skeleton-based human action recognition in computer vision.