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

Generation of Action Potential in Skeletal Muscles01:24

Generation of Action Potential in Skeletal Muscles

8.0K
Every cell in the body maintains a membrane potential due to an uneven distribution of positive and negative charges across its plasma membrane. The membrane potential is measured in millivolts and quantifies the difference in charge across the membrane.
Like neurons, muscle cells are also regarded as excitable due to their capacity to change in response to stimuli, primarily due to voltage-gated ion channels embedded in their plasma membranes, which get activated by alterations in the...
8.0K
Muscle Coordination and Action01:24

Muscle Coordination and Action

2.9K
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....
2.9K
Carbon Skeletons01:12

Carbon Skeletons

113.5K
Life on Earth is carbon-based, as all macromolecules that make up living organisms contain carbon atoms. All organic compounds have a carbon backbone. Each carbon atom is tetravalent and can bond with four other atoms, making it an extraordinarily flexible component of biological molecules. Because carbon’s valence electrons are stable, it rarely becomes an ion. As the carbon chain increases in length, structural modifications such as ring structures, double bonds, and branching side...
113.5K
Fixed Action Patterns01:06

Fixed Action Patterns

17.2K
A fixed action pattern (FAP) is a specific, hard-wired sequence of behaviors that occurs in response to an external stimulus, called a sign stimulus. The behavior is “fixed” because it is essentially unchangeable—proceeding similarly across individuals of a species every time it occurs.
17.2K
Propagation of Action Potentials01:23

Propagation of Action Potentials

8.4K
The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
8.4K
Classification of Bones01:18

Classification of Bones

9.2K
The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The...
9.2K

You might also read

Related Articles

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

Sort by
Same author

An Explainable Student Fatigue Monitoring Module with Joint Facial Representation.

Sensors (Basel, Switzerland)·2023
Same author

Deep level set method for optic disc and cup segmentation on fundus images.

Biomedical optics express·2021
Same author

Image-level supervised segmentation for human organs with confidence cues.

Physics in medicine and biology·2021
Same author

Robust Nonparametric Distribution Transfer with Exposure Correction for Image Neural Style Transfer.

Sensors (Basel, Switzerland)·2020
Same author

A multiresolution mixture generative adversarial network for video super-resolution.

PloS one·2020
Same author

Graph convolutional network based optic disc and cup segmentation on fundus images.

Biomedical optics express·2020

Related Experiment Video

Updated: Dec 17, 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

2.1K

GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition.

Wensong Chan1, Zhiqiang Tian1, Yang Wu2

  • 1School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China.

Sensors (Basel, Switzerland)
|June 25, 2020
PubMed
Summary

This study introduces novel graph convolutional modules and gated temporal convolutions for skeleton-based action recognition. The method effectively captures implicit joint connections, improving action classification accuracy on benchmark datasets.

Keywords:
action recognitiondeep learninggated convolutional neural networksgraph convolutional networks

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.0K
Corticospinal Excitability Modulation During Action Observation
12:33

Corticospinal Excitability Modulation During Action Observation

Published on: December 31, 2013

9.3K

Related Experiment Videos

Last Updated: Dec 17, 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

2.1K
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.0K
Corticospinal Excitability Modulation During Action Observation
12:33

Corticospinal Excitability Modulation During Action Observation

Published on: December 31, 2013

9.3K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Artificial Intelligence

Background:

  • Skeleton-based action recognition leverages human pose data for understanding activities.
  • Graph Convolutional Networks (GCNs) have advanced skeleton-based action recognition.
  • Existing GCN models often rely on fixed, hand-crafted adjacency matrices, neglecting crucial implicit joint relationships.

Purpose of the Study:

  • To develop an action-specific graph convolutional module for extracting implicit joint connections.
  • To introduce a gated temporal convolution for filtering redundant temporal information.
  • To enhance the accuracy and robustness of skeleton-based action recognition models.

Main Methods:

  • Proposed an action-specific graph convolutional module to learn dynamic, action-dependent joint relationships.
  • Developed a gated temporal convolution operation to refine temporal information, reducing noise and redundancy.
  • Evaluated the proposed method on large-scale datasets: NTU-RGB+D, Kinetics, and NTU-RGB+D 120.

Main Results:

  • The proposed method demonstrated superior performance compared to existing approaches on multiple benchmark datasets.
  • Ablation studies confirmed the effectiveness of both the action-specific graph convolutional module and the gated temporal convolution.
  • The model successfully identified discriminative implicit connections between human body joints for accurate action classification.

Conclusions:

  • The novel approach significantly advances skeleton-based action recognition by effectively utilizing implicit joint information and temporal dynamics.
  • The action-specific graph convolutional module and gated temporal convolution are key innovations for improved performance.
  • The method offers a more comprehensive and accurate way to interpret human actions from skeletal data.