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

You might also read

Related Articles

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

Sort by
Same author

simDP: Sim-to-Real Transfer with Shared Action Spaces.

Sensors (Basel, Switzerland)·2026
Same author

Sensing the Action: Rethinking Sensor Modalities and Multi-Modal Fusion in Vision-Language-Action Models for Robotic Manipulation.

Sensors (Basel, Switzerland)·2026
Same author

Keyword-Conditioned Image Segmentation via the Cross-Attentive Alignment of Language and Vision Sensor Data.

Sensors (Basel, Switzerland)·2025
Same author

Scene Graph and Natural Language-Based Semantic Image Retrieval Using Vision Sensor Data.

Sensors (Basel, Switzerland)·2025
Same author

Rethinking Attention Mechanisms in Vision Transformers with Graph Structures.

Sensors (Basel, Switzerland)·2024
Same author

High-Resolution Tactile-Sensation Diagnostic Imaging System for Thyroid Cancer.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Aug 17, 2025

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

4.0K

Lightweight Semantic-Guided Neural Networks Based on Single Head Attention for Action Recognition.

Seon-Bin Kim1, Chanhyuk Jung1, Byeong-Il Kim1

  • 1Department of Computer Engineering, Keimyung University, Daegu 42601, Republic of Korea.

Sensors (Basel, Switzerland)
|December 11, 2022
PubMed
Summary

This study introduces a new model for skeleton-based action recognition, enhancing efficiency for real-time performance on low-end devices. The proposed method improves upon existing techniques by better capturing local dependencies in human poses.

Keywords:
action recognitiongraph convolutional networkssemantic-guided neural networkssingle head attentionskeletal structure

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

604
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

480

Related Experiment Videos

Last Updated: Aug 17, 2025

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

4.0K
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

604
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

480

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Machine Learning

Background:

  • Skeleton-based action recognition leverages graph convolutional networks (GCNs) by modeling human poses as graphs.
  • Semantic-guided neural networks (SGNs) offer fast action recognition by hierarchically learning spatial-temporal features using GCNs.
  • Existing SGNs have limitations in recognizing actions where local node dependencies are crucial due to their focus on global feature learning.

Purpose of the Study:

  • To address the limitations of SGNs in capturing local feature dependencies for skeleton-based action recognition.
  • To develop a novel model that enables real-time action recognition on resource-constrained devices.
  • To enhance the performance of action recognition by integrating a single head attention mechanism.

Main Methods:

  • Proposed a novel model, SGN-SHA, by combining a semantic-guided neural network (SGN) with a single head attention (SHA) mechanism.
  • SHA is designed to overcome the limitations of SGNs in learning local features.
  • The SGN-SHA model was evaluated on various benchmark datasets for action recognition.

Main Results:

  • The SGN-SHA model demonstrated significantly reduced computational complexity compared to existing methods.
  • Achieved performance comparable to existing SGN models and other state-of-the-art approaches.
  • Successfully enabled real-time action recognition capabilities, particularly on low-end devices.

Conclusions:

  • The proposed SGN-SHA model effectively integrates global and local feature learning for skeleton-based action recognition.
  • Offers a computationally efficient solution for real-time action recognition, suitable for deployment on devices with limited resources.
  • Represents a significant advancement in the field, balancing performance and efficiency.