Search research articles

Related Concept Videos

Classification of Bones

Classification of Bones

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...

You might also read

Related Articles

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

Sort by

Same author

ICT-Net: An Integrated Convolution and Transformer-Based Network for Complex Liver and Liver Tumor Region Segmentation.

IEEE journal of translational engineering in health and medicine·2025

Same journal

Multiphysics Investigation on Thermal Characteristics of Internal Bio-Inspired V-Ribbed Cooling Channels for Outer Rotor PMSM.

Biomimetics (Basel, Switzerland)·2026

Same journal

Smart Logistics Model for Supply Chain Management via Brain-Inspired Geometric Deep Networks.

Biomimetics (Basel, Switzerland)·2026

Same journal

A Systematic Taxonomy of the Sunflower Optimization Algorithm: Variants, Hybridization Strategies, Applications, and Research Directions.

Biomimetics (Basel, Switzerland)·2026

Same journal

Toward a Compositional Theory of Trust in Embodied Intelligence: A QNLP Framework for Modeling Context, Interaction, and Trustworthiness.

Biomimetics (Basel, Switzerland)·2026

Same journal

Empirical Logic for Bio-Inspired Soft Computing: Illustrative Applications in Control Engineering and Cluster Analysis.

Biomimetics (Basel, Switzerland)·2026

Same journal

A Modified Multi-Strategy Dhole Optimization Algorithm and Its Engineering Applications.

Biomimetics (Basel, Switzerland)·2026

See all related 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

Search research articles

Related Experiment Video

Updated: Nov 9, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Multi-Modal Enhancement Transformer Network for Skeleton-Based Human Interaction Recognition.

Qianshuo Hu¹, Haijun Liu¹

¹School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China.

Biomimetics (Basel, Switzerland)

|March 27, 2024

Summary

This summary is machine-generated.

This study introduces the multi-modal enhancement transformer (ME-Former) for improved skeleton-based human interaction recognition. ME-Former effectively integrates complementary skeletal features and enhances the capture of two-person interactions.

Keywords:

human interaction recognition hypergraph representation skeleton data transformer

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 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

Related Experiment Videos

Last Updated: Nov 9, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 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

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Skeleton-based human interaction recognition is crucial in computer vision.
Graph Convolutional Networks (GCNs) model skeletons but struggle with multi-modal feature integration and two-person interactions.

Purpose of the Study:

To address limitations in existing GCN-based methods for skeleton-based human interaction recognition.
To propose a novel network that effectively utilizes complementary skeletal features and captures intricate two-person interactions.

Main Methods:

Developed the multi-modal enhancement transformer (ME-Former) network.
Introduced a multi-modal enhancement (ME) module with multi-head cross-modal attention (MH-CA) and a two-person hypergraph self-attention (TH-SA) block.
Proposed a two-person skeleton topology and hypergraph representation for enhanced interaction modeling.
Incorporated a context progressive fusion (CPF) block for efficient feature transformation.

Main Results:

ME-Former demonstrated superior performance on the NTU-RGB+D 60 and NTU-RGB+D 120 datasets.
The proposed MH-CA and TH-SA blocks effectively enhanced skeletal features and captured spatial dependencies.
The CPF block enabled efficient fusion of multi-modal skeletal features.

Conclusions:

ME-Former significantly outperforms state-of-the-art methods in skeleton-based human interaction recognition.
The proposed architecture effectively addresses the challenges of multi-modal feature integration and two-person interaction modeling.
ME-Former offers a promising direction for advancing human interaction recognition research.