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 Experiment Video

Updated: Jan 18, 2026

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

5.3K

SSTA-ResT: Soft Spatiotemporal Attention ResNet Transformer for Argentine Sign Language Recognition.

Xianru Liu1, Zeru Zhou1, E Xia1

  • 1School of Automation, Central South University, Changsha 410083, China.

Sensors (Basel, Switzerland)
|September 13, 2025
PubMed
Summary

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

In Silico and In Vivo Pharmacokinetic Evaluation of 84-B10, a Novel Drug Candidate against Acute Kidney Injury and Chronic Kidney Disease.

Molecules (Basel, Switzerland)·2024
Same author

Cancer-associated fibroblast expression of glutamine fructose-6-phosphate aminotransferase 2 (GFPT2) is a prognostic marker in gastric cancer.

The journal of pathology. Clinical research·2023
Same author

Association between Vitamin A and E Forms and Prostate Cancer Risk in the Singapore Prostate Cancer Study.

Nutrients·2023
Same author

Prognostic analysis of patients with breast cancer based on tumor mutational burden and DNA damage repair genes.

Frontiers in oncology·2023
Same author

Chromosome-level genome assembly of Murraya paniculata sheds light on biosynthesis of floral volatiles.

BMC biology·2023
Same author

Exposure to cooking fumes is associated with perturbations in nasal microbiota composition: A pilot study.

Environmental research·2023

This study introduces SSTA-ResT, a novel framework for sign language recognition that effectively captures dynamic and temporal information. The advanced model significantly improves accuracy and inclusivity for deaf and hearing individuals.

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Human-Computer Interaction

Background:

  • Sign language recognition technology is vital for bridging communication gaps and promoting social inclusivity.
  • Traditional methods using static images fail to capture the dynamic nature of sign language, limiting real-world applications.
  • Developing robust sign language recognition systems is crucial for enhancing accessibility for the deaf community.

Purpose of the Study:

  • To propose an effective framework for sign language recognition that addresses the limitations of conventional methods.
  • To enhance the capture of dynamic and temporal information crucial for accurate sign language interpretation.
  • To improve social inclusivity by facilitating better communication between deaf and hearing individuals.

Main Methods:

Keywords:
Argentine Sign Language recognitionResNetTransformerspatiotemporal attention

Related Experiment Videos

Last Updated: Jan 18, 2026

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

5.3K
  • The SSTA-ResT framework integrates ResNet for spatial feature extraction.
  • A soft spatiotemporal attention (SSTA) module enhances dual-path representations and spatiotemporal associations.
  • Transformer encoders are utilized to capture long-range temporal dependencies in sign language videos.

Main Results:

  • The SSTA-ResT framework achieved 96.25% accuracy, 97.18% precision, and an F1 score of 0.9671 on the LSA64 Argentine Sign Language dataset.
  • Performance metrics surpassed existing methods across all evaluated metrics.
  • The model maintains a low parameter count (11.66 M), indicating efficiency.

Conclusions:

  • The SSTA-ResT framework demonstrates superior effectiveness and practicality for sign language video recognition.
  • The integration of ResNet, SSTA, and Transformer encoders provides a robust solution for capturing complex sign language dynamics.
  • This advancement holds significant potential for improving communication accessibility and social inclusion for deaf individuals.