POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Joshi, Abhinav, Sharma, Vaibhav, Singh, Sanjeet, Modi, Ashutosh
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911244206735360
author Joshi, Abhinav
Sharma, Vaibhav
Singh, Sanjeet
Modi, Ashutosh
author_facet Joshi, Abhinav
Sharma, Vaibhav
Singh, Sanjeet
Modi, Ashutosh
contents Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose POSESTITCH-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings.
format Preprint
id arxiv_https___arxiv_org_abs_2511_00270
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation
Joshi, Abhinav
Sharma, Vaibhav
Singh, Sanjeet
Modi, Ashutosh
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Sign language translation remains a challenging task due to the scarcity of large-scale, sentence-aligned datasets. Prior arts have focused on various feature extraction and architectural changes to support neural machine translation for sign languages. We propose POSESTITCH-SLT, a novel pre-training scheme that is inspired by linguistic-templates-based sentence generation technique. With translation comparison on two sign language datasets, How2Sign and iSign, we show that a simple transformer-based encoder-decoder architecture outperforms the prior art when considering template-generated sentence pairs in training. We achieve BLEU-4 score improvements from 1.97 to 4.56 on How2Sign and from 0.55 to 3.43 on iSign, surpassing prior state-of-the-art methods for pose-based gloss-free translation. The results demonstrate the effectiveness of template-driven synthetic supervision in low-resource sign language settings.
title POSESTITCH-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translation
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2511.00270