Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Analytical study on steady seepage of a foundation pit adjacent to a structure.

Scientific reports·2025

Same author

PKG-Mediated Phosphorylation of TOP2A Activates HDAC to Drive Photoreceptor Cell Death in rd1 Mouse Inherited Retinal Degeneration.

Journal of neurochemistry·2025

Same author

A Circularly Polarized Broadband Composite Spiral Antenna for Ground Penetrating Radar.

Sensors (Basel, Switzerland)·2025

Same author

Fabricating a Three-Dimensional Surface-Enhanced Raman Scattering Substrate Using Hydrogel-Loaded Freeze-Induced Silver Nanoparticle Aggregates for the Highly Sensitive Detection of Organic Pollutants in Seawater.

Sensors (Basel, Switzerland)·2025

Same author

Investigating immune cell infiltration and gene expression features in pterygium pathogenesis.

Scientific reports·2025

Same author

Clinical characteristics and risk factors for readmission after deep anterior lamellar keratoplasty: a nationwide, cross-sectional, multicenter study.

BMC ophthalmology·2025

Search research articles

Related Experiment Video

Updated: Jun 27, 2025

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

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

Published on: April 21, 2023

ST-TGR: Spatio-Temporal Representation Learning for Skeleton-Based Teaching Gesture Recognition.

Zengzhao Chen^1,2, Wenkai Huang¹, Hai Liu^1,2

¹Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, China.

Sensors (Basel, Switzerland)

|April 27, 2024

Summary

This summary is machine-generated.

This study introduces skeleton-based teaching gesture recognition (ST-TGR) for analyzing teacher movements in classrooms. The new method achieves higher accuracy and speed in recognizing dynamic gestures compared to existing models.

Keywords:

action recognition classroom scenario pose estimation teaching gesture

More Related Videos

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Jun 27, 2025

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

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

Published on: April 21, 2023

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

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

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

Published on: December 15, 2023

Area of Science:

Computer Science
Artificial Intelligence
Educational Technology

Background:

Current gesture recognition research in education primarily focuses on static student gestures.
Analyzing dynamic teacher gestures in multi-person scenarios presents significant challenges.

Purpose of the Study:

To develop a novel skeleton-based teaching gesture recognition (ST-TGR) method.
To accurately recognize dynamic teacher gestures in complex teaching environments.

Main Methods:

Utilized RTMPose for extracting teacher skeleton keypoints.
Employed a MoGRU (Multi-scale Bidirectional Gated Recurrent Unit) network with attention for action classification.
Trained and validated the model on diverse datasets (NTU RGB+D 60, UT-Kinect, SBU Kinect, Florence 3D).

Main Results:

The proposed ST-TGR method demonstrated superior performance over baseline models.
Achieved enhanced recognition accuracy for dynamic teaching gestures.
Showcased improved recognition speed in comparative experiments.

Conclusions:

Skeleton-based analysis effectively captures dynamic teacher gestures.
The ST-TGR method offers a robust solution for classroom gesture recognition.
This technology has potential applications in teacher evaluation and enhanced online teaching.