BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Azad, Sayad Ibna, Rahman, Md. Atiqur
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908792059330560
author Azad, Sayad Ibna
Rahman, Md. Atiqur
author_facet Azad, Sayad Ibna
Rahman, Md. Atiqur
contents We introduce BdSL-SPOTER, a pose-based transformer framework for accurate and efficient recognition of Bengali Sign Language (BdSL). BdSL-SPOTER extends the SPOTER paradigm with cultural specific preprocessing and a compact four-layer transformer encoder featuring optimized learnable positional encodings, while employing curriculum learning to enhance generalization on limited data and accelerate convergence. On the BdSLW60 benchmark, it achieves 97.92% Top-1 validation accuracy, representing a 22.82% improvement over the Bi-LSTM baseline, all while keeping computational costs low. With its reduced number of parameters, lower FLOPs, and higher FPS, BdSL-SPOTER provides a practical framework for real-world accessibility applications and serves as a scalable model for other low-resource regional sign languages.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12103
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation
Azad, Sayad Ibna
Rahman, Md. Atiqur
Computer Vision and Pattern Recognition
We introduce BdSL-SPOTER, a pose-based transformer framework for accurate and efficient recognition of Bengali Sign Language (BdSL). BdSL-SPOTER extends the SPOTER paradigm with cultural specific preprocessing and a compact four-layer transformer encoder featuring optimized learnable positional encodings, while employing curriculum learning to enhance generalization on limited data and accelerate convergence. On the BdSLW60 benchmark, it achieves 97.92% Top-1 validation accuracy, representing a 22.82% improvement over the Bi-LSTM baseline, all while keeping computational costs low. With its reduced number of parameters, lower FLOPs, and higher FPS, BdSL-SPOTER provides a practical framework for real-world accessibility applications and serves as a scalable model for other low-resource regional sign languages.
title BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.12103