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

Efficacy and Safety of PF-07038124 in Patients With Atopic Dermatitis and Plaque Psoriasis: A Randomized Clinical Trial.

JAMA dermatology·2023
Same author

Improving enteral nutrition tolerance and protein intake maybe beneficial to intensive care unit patients.

Scientific reports·2023
Same author

Efficacy and Safety of Dual Anti-HER2 Blockade and Docetaxel With or Without Carboplatin as Neoadjuvant Regimen for Treatment of HER2-Positive Breast Cancer.

Technology in cancer research & treatment·2023
Same author

Boosting Low-Temperature CO<sub>2</sub> Hydrogenation over Ni-based Catalysts by Tuning Strong Metal-Support Interactions.

Angewandte Chemie (International ed. in English)·2023
Same author

A new direction in Chinese herbal medicine ameliorates for type 2 diabetes mellitus: Focus on the potential of mitochondrial respiratory chain complexes.

Journal of ethnopharmacology·2023
Same author

Computational Insight into the Nature and Strength of the π-Hole Type Chalcogen∙∙∙Chalcogen Interactions in the XO<sub>2</sub>∙∙∙CH<sub>3</sub>YCH<sub>3</sub> Complexes (X = S, Se, Te; Y = O, S, Se, Te).

International journal of molecular sciences·2023

Related Experiment Video

Updated: Mar 4, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

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

Published on: April 21, 2023

2.4K

Hand gesture 3D pose estimation method based on swin transformer and CNN.

Rong Dang1,2, Gang Feng3

  • 1School of Architecture, Tianjin University, Tianjin, 300073, China. drong_7788@tju.edu.cn.

Scientific Reports
|March 2, 2026
PubMed
Summary

This study introduces a novel gesture pose estimation method using depth images. The approach enhances accuracy by capturing joint relationships and global features, outperforming existing models.

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

851
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

2.3K

Related Experiment Videos

Last Updated: Mar 4, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

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

Published on: April 21, 2023

2.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

851
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

2.3K

Area of Science:

  • Computer Vision
  • Machine Learning
  • Human-Computer Interaction

Background:

  • Existing gesture pose estimation methods struggle with singular feature extraction and fail to capture long-range joint relationships, limiting accuracy.
  • Depth image data offers rich spatial information crucial for precise gesture recognition.

Purpose of the Study:

  • To develop an advanced gesture pose estimation method utilizing depth images.
  • To overcome the limitations of current methods in feature extraction and topological relationship modeling.

Main Methods:

  • A hybrid approach combining convolutional networks for initial feature extraction and Swin Transformer for global context and joint relationships.
  • Hierarchical feature processing using a U-shaped network to preserve multi-resolution local joint information.
  • Integration of 2D Gaussian heatmaps for improved keypoint localization and network supervision.

Main Results:

  • The proposed method achieved a significant reduction in average squared error, outperforming baseline models by 4.776 mm.
  • Experimental validation on a newly constructed dataset demonstrated superior performance compared to state-of-the-art pose estimation networks.
  • The method effectively captures both local joint details and global gesture topology.

Conclusions:

  • The novel gesture pose estimation method significantly improves accuracy and robustness by integrating depth information and advanced network architectures.
  • The findings suggest a promising direction for more precise and reliable human-computer interaction through gesture recognition.
  • This research addresses key challenges in gesture pose estimation, offering a more effective solution for various applications.