Next Article in Journal
Intensified Rainfall, Growing Floods: Projecting Urban Drainage Challenges in South-Central China Under Climate Change Scenarios
Previous Article in Journal
The Dual Role of Metformin: Repurposing an Antidiabetic Drug for Cancer Therapy
Previous Article in Special Issue
A Survey on Multi-User Conversational Interfaces
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 15
Issue 21
10.3390/app152111571
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Isolated German Sign Language Recognition for Classifying Polar Answers Using Landmarks and Lightweight Transformers

by
Cristina Luna-Jiménez
1,*,
Lennart Eing
1,
Sergio Esteban-Romero
2,
Manuel Gil-Martín
2 and
Elisabeth André
1
1
Chair for Human-Centered Artificial Intelligence, Faculty of Applied Computer Science, University of Augsburg, 86159 Augsburg, Germany
2
Grupo de Tecnología del Habla y Aprendizaje Automático (THAU Group), Information Processing and Telecommunications Center, E.T.S.I. de Telecomunicación, Universidad Politécnica de Madrid (UPM), 28040 Madrid, Spain
*
Author to whom correspondence should be addressed.
Appl. Sci. 2025, 15(21), 11571; https://doi.org/10.3390/app152111571
Submission received: 28 September 2025 / Revised: 24 October 2025 / Accepted: 27 October 2025 / Published: 29 October 2025
(This article belongs to the Special Issue Affective Computing for Human–Computer Interactions)
Versions Notes

Abstract

Sign Languages are the primary communication modality of deaf communities, yet building effective Isolated Sign Language Recognition (ISLR) systems remains difficult under data limitations. In this work, we curated a sub-dataset from the DGS-Korpus focused on recognizing affirmations and negations (polar answers) in German Sign Language (DGS). We designed lightweight transformer models using landmark-based inputs and evaluated them on two tasks: the binary classification of affirmations versus negations (binary semantic recognition) and the multi-class recognition of sign variations expressing positive or negative replies (multi-class gloss recognition). The main contribution of the article, hence, relies on the exploration of models for performing polar answer recognition in DGS and the exploration of differences between performing multi-class or binary class classification. Our best binary model achieved an accuracy of 97.71% using only hand landmarks without Positional Encoding, highlighting the potential of lightweight landmark-based transformers for efficient ISLR in constrained domains.
Keywords: isolated sign language recognition; transformers; machine learning; human-computer interaction; accessibility isolated sign language recognition; transformers; machine learning; human-computer interaction; accessibility

Share and Cite

MDPI and ACS Style

Luna-Jiménez, C.; Eing, L.; Esteban-Romero, S.; Gil-Martín, M.; André, E. Isolated German Sign Language Recognition for Classifying Polar Answers Using Landmarks and Lightweight Transformers. Appl. Sci. 2025, 15, 11571. https://doi.org/10.3390/app152111571

AMA Style

Luna-Jiménez C, Eing L, Esteban-Romero S, Gil-Martín M, André E. Isolated German Sign Language Recognition for Classifying Polar Answers Using Landmarks and Lightweight Transformers. Applied Sciences. 2025; 15(21):11571. https://doi.org/10.3390/app152111571

Chicago/Turabian Style

Luna-Jiménez, Cristina, Lennart Eing, Sergio Esteban-Romero, Manuel Gil-Martín, and Elisabeth André. 2025. "Isolated German Sign Language Recognition for Classifying Polar Answers Using Landmarks and Lightweight Transformers" Applied Sciences 15, no. 21: 11571. https://doi.org/10.3390/app152111571

APA Style

Luna-Jiménez, C., Eing, L., Esteban-Romero, S., Gil-Martín, M., & André, E. (2025). Isolated German Sign Language Recognition for Classifying Polar Answers Using Landmarks and Lightweight Transformers. Applied Sciences, 15(21), 11571. https://doi.org/10.3390/app152111571

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop