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

MicroRNA-1224 Splicing CircularRNA-Filip1l in an Ago2-Dependent Manner Regulates Chronic Inflammatory Pain via Targeting Ubr5.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2019

Same author

Treatment of clinical T4 stage superior sulcus non-small cell lung cancer: a propensity-matched analysis of the surveillance, epidemiology, and end results database.

Bioscience reports·2019

Same author

Machine learning framework for assessment of microbial factory performance.

PloS one·2019

Same author

Low Pathogenic Avian Influenza A (H5N7) Virus Isolated from a Domestic Duck in Dongting Lake Wetland of China, 2016.

Virologica Sinica·2019

Same author

Nomograms for predicting survival outcomes in patients with primary tracheal tumors: a large population-based analysis.

Cancer management and research·2018

Same author

The role of metabolism in the pathogenesis of systemic sclerosis.

Metabolism: clinical and experimental·2018

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Oct 15, 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

Adaptive Attention Memory Graph Convolutional Networks for Skeleton-Based Action Recognition.

Di Liu¹, Hui Xu¹, Jianzhong Wang¹

¹College of Information Sciences and Technology, Northeast Normal University, Changchun 130117, China.

Sensors (Basel, Switzerland)

|October 26, 2021

Summary

This summary is machine-generated.

This study introduces Adaptive Attention Memory Graph Convolutional Networks (AAM-GCN) for improved human action recognition from skeleton data. The novel approach enhances accuracy by adaptively modeling spatial configurations and capturing temporal features using an attention mechanism.

Keywords:

action recognition attention graph convolutional networks skeleton sequence

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Oct 15, 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

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Graph Convolutional Networks (GCNs) show promise for action recognition.
Key challenges include adaptive graph structure, key frame selection, and discriminative feature extraction.

Purpose of the Study:

To propose a novel Adaptive Attention Memory Graph Convolutional Network (AAM-GCN) for enhanced human action recognition using skeleton data.
To address limitations in current GCN-based action recognition methods.

Main Methods:

Utilized GCN for adaptive spatial modeling of skeleton data.
Employed Gated Recurrent Unit (GRU) with an attention mechanism for temporal feature extraction.
Incorporated a multi-bidirectional GRU memory module for capturing past and future temporal information.
Applied attention to select key frames for discriminative feature extraction.

Main Results:

The proposed AAM-GCN model demonstrated superior performance compared to existing state-of-the-art methods.
Achieved significant improvements in action recognition accuracy on benchmark datasets (Kinetics, NTU RGB+D, HDM05).

Conclusions:

The AAM-GCN effectively models spatial-temporal dynamics for human action recognition.
The adaptive graph structure, attention mechanism, and memory module contribute to improved recognition accuracy.