Work

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

Year: 2025

Type: article

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.

Source: Applied Sciences

DOI: 10.3390/app152111571

Authors: Cristina Luna-Jiménez, Lennart Eing, Sergio Esteban-Romero, Manuel Gil-Martín, Elisabeth André

Institutions: University of Augsburg, Information Processing and Telecommunications Center, Universidad Politécnica de Madrid

Language: English

Topic: Hand Gesture Recognition Systems

Subfield: Human-Computer Interaction

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,896

Funders: European Commission, Bundesministerium für Bildung und Forschung, Ministerio de Ciencia e Innovación, Agencia Estatal de Investigación