Stack Transformer Based Spatial-Temporal Attention Model for Dynamic Sign Language and Fingerspelling Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hirooka, Koki, Miah, Abu Saleh Musa, Murakami, Tatsuya, Hasan, Md. Al Mehedi, Hwang, Yong Seok, Shin, Jungpil
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911254877044736
author Hirooka, Koki
Miah, Abu Saleh Musa
Murakami, Tatsuya
Hasan, Md. Al Mehedi
Hwang, Yong Seok
Shin, Jungpil
author_facet Hirooka, Koki
Miah, Abu Saleh Musa
Murakami, Tatsuya
Hasan, Md. Al Mehedi
Hwang, Yong Seok
Shin, Jungpil
contents Hand gesture-based Sign Language Recognition (SLR) serves as a crucial communication bridge between deaf and non-deaf individuals. While Graph Convolutional Networks (GCNs) are common, they are limited by their reliance on fixed skeletal graphs. To overcome this, we propose the Sequential Spatio-Temporal Attention Network (SSTAN), a novel Transformer-based architecture. Our model employs a hierarchical, stacked design that sequentially integrates Spatial Multi-Head Attention (MHA) to capture intra-frame joint relationships and Temporal MHA to model long-range inter-frame dependencies. This approach allows the model to efficiently learn complex spatio-temporal patterns without predefined graph structures. We validated our model through extensive experiments on diverse, large-scale datasets (WLASL, JSL, and KSL). A key finding is that our model, trained entirely from scratch, achieves state-of-the-art (SOTA) performance in the challenging fingerspelling categories (JSL and KSL). Furthermore, it establishes a new SOTA for skeleton-only methods on WLASL, outperforming several approaches that rely on complex self-supervised pre-training. These results demonstrate our model's high data efficiency and its effectiveness in capturing the intricate dynamics of sign language. The official implementation is available at our GitHub repository: \href{https://github.com/K-Hirooka-Aizu/skeleton-slr-transformer}{https://github.com/K-Hirooka-Aizu/skeleton-slr-transformer}.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16855
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stack Transformer Based Spatial-Temporal Attention Model for Dynamic Sign Language and Fingerspelling Recognition
Hirooka, Koki
Miah, Abu Saleh Musa
Murakami, Tatsuya
Hasan, Md. Al Mehedi
Hwang, Yong Seok
Shin, Jungpil
Computer Vision and Pattern Recognition
Hand gesture-based Sign Language Recognition (SLR) serves as a crucial communication bridge between deaf and non-deaf individuals. While Graph Convolutional Networks (GCNs) are common, they are limited by their reliance on fixed skeletal graphs. To overcome this, we propose the Sequential Spatio-Temporal Attention Network (SSTAN), a novel Transformer-based architecture. Our model employs a hierarchical, stacked design that sequentially integrates Spatial Multi-Head Attention (MHA) to capture intra-frame joint relationships and Temporal MHA to model long-range inter-frame dependencies. This approach allows the model to efficiently learn complex spatio-temporal patterns without predefined graph structures. We validated our model through extensive experiments on diverse, large-scale datasets (WLASL, JSL, and KSL). A key finding is that our model, trained entirely from scratch, achieves state-of-the-art (SOTA) performance in the challenging fingerspelling categories (JSL and KSL). Furthermore, it establishes a new SOTA for skeleton-only methods on WLASL, outperforming several approaches that rely on complex self-supervised pre-training. These results demonstrate our model's high data efficiency and its effectiveness in capturing the intricate dynamics of sign language. The official implementation is available at our GitHub repository: \href{https://github.com/K-Hirooka-Aizu/skeleton-slr-transformer}{https://github.com/K-Hirooka-Aizu/skeleton-slr-transformer}.
title Stack Transformer Based Spatial-Temporal Attention Model for Dynamic Sign Language and Fingerspelling Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.16855