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

2.8K
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....
2.8K
Carbon Skeletons01:12

Carbon Skeletons

113.3K
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...
113.3K

You might also read

Related Articles

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

Sort by
Same author

Hierarchical Contrastive Learning for Semantic Segmentation.

IEEE transactions on neural networks and learning systems·2025
Same author

MoS<sub>2</sub> quantum dot-decorated CNT networks as a sulfur host for enhanced electrochemical kinetics in advanced lithium-sulfur batteries.

Nanoscale advances·2024
Same author

Template assisted preparation of silicone (polydimethylsiloxane) elastomers and their self-cleaning application.

RSC advances·2022
Same author

An Efficient Sampling-Based Attention Network for Semantic Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2022
Same author

Enhanced Bounding Box Estimation with Distribution Calibration for Visual Tracking.

Sensors (Basel, Switzerland)·2021
Same author

Question-Guided Erasing-Based Spatiotemporal Attention Learning for Video Question Answering.

IEEE transactions on neural networks and learning systems·2021

Related Experiment Video

Updated: Dec 6, 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

2.0K

Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks.

Lei Shi, Yifan Zhang, Jian Cheng

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |October 9, 2020
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel adaptive graph convolutional network for skeleton-based action recognition. The model dynamically learns graph structures and incorporates bone information, significantly improving recognition accuracy over state-of-the-art methods.

    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

    4.9K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    675

    Related Experiment Videos

    Last Updated: Dec 6, 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

    2.0K
    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

    4.9K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    675

    Area of Science:

    • Computer Vision
    • Machine Learning
    • Artificial Intelligence

    Background:

    • Graph convolutional networks (GCNs) excel at skeleton-based action recognition but often use fixed graph topologies.
    • Previous GCN models overlook informative second-order skeleton data like bone length and orientation.
    • Action recognition requires models adaptable to diverse data and hierarchical structures.

    Purpose of the Study:

    • To propose a multi-stream attention-enhanced adaptive graph convolutional neural network (MS-AAGCN) for improved skeleton-based action recognition.
    • To enable data-driven, end-to-end learning of flexible graph topologies.
    • To leverage both joint and bone information, including motion dynamics, for enhanced discriminative power.

    Main Methods:

    • Developed an adaptive graph convolutional layer with data-driven topology learning (uniform or individual).
    • Integrated a spatial-temporal-channel attention module to focus on salient joints, frames, and features.
    • Employed a multi-stream framework to simultaneously process joint, bone, and motion information.

    Main Results:

    • The proposed MS-AAGCN achieved state-of-the-art performance on NTU-RGBD and Kinetics-Skeleton datasets.
    • Adaptive graph topology learning enhanced model flexibility and generality.
    • Incorporating bone and motion information significantly boosted recognition accuracy.

    Conclusions:

    • The MS-AAGCN offers a more flexible and powerful approach to skeleton-based action recognition.
    • Data-driven adaptive graph learning and multi-stream feature fusion are key to superior performance.
    • The model effectively utilizes richer skeleton data for more accurate human action understanding.