Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jang, Youngjoon, Momeni, Liliane, Jiang, Zifan, Chung, Joon Son, Varol, Gül, Zisserman, Andrew
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912754950995968
author Jang, Youngjoon
Momeni, Liliane
Jiang, Zifan
Chung, Joon Son
Varol, Gül
Zisserman, Andrew
author_facet Jang, Youngjoon
Momeni, Liliane
Jiang, Zifan
Chung, Joon Son
Varol, Gül
Zisserman, Andrew
contents Our aim is to develop a unified model for sign language understanding, that performs sign language translation (SLT) and sign-subtitle alignment (SSA). Together, these two tasks enable the conversion of continuous signing videos into spoken language text and also the temporal alignment of signing with subtitles -- both essential for practical communication, large-scale corpus construction, and educational applications. To achieve this, our approach is built upon three components: (i) a lightweight visual backbone that captures manual and non-manual cues from human keypoints and lip-region images while preserving signer privacy; (ii) a Sliding Perceiver mapping network that aggregates consecutive visual features into word-level embeddings to bridge the vision-text gap; and (iii) a multi-task scalable training strategy that jointly optimises SLT and SSA, reinforcing both linguistic and temporal alignment. To promote cross-linguistic generalisation, we pretrain our model on large-scale sign-text corpora covering British Sign Language (BSL) and American Sign Language (ASL) from the BOBSL and YouTube-SL-25 datasets. With this multilingual pretraining and strong model design, we achieve state-of-the-art results on the challenging BOBSL (BSL) dataset for both SLT and SSA. Our model also demonstrates robust zero-shot generalisation and finetuned SLT performance on How2Sign (ASL), highlighting the potential of scalable translation across different sign languages.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08040
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
Jang, Youngjoon
Momeni, Liliane
Jiang, Zifan
Chung, Joon Son
Varol, Gül
Zisserman, Andrew
Computer Vision and Pattern Recognition
Our aim is to develop a unified model for sign language understanding, that performs sign language translation (SLT) and sign-subtitle alignment (SSA). Together, these two tasks enable the conversion of continuous signing videos into spoken language text and also the temporal alignment of signing with subtitles -- both essential for practical communication, large-scale corpus construction, and educational applications. To achieve this, our approach is built upon three components: (i) a lightweight visual backbone that captures manual and non-manual cues from human keypoints and lip-region images while preserving signer privacy; (ii) a Sliding Perceiver mapping network that aggregates consecutive visual features into word-level embeddings to bridge the vision-text gap; and (iii) a multi-task scalable training strategy that jointly optimises SLT and SSA, reinforcing both linguistic and temporal alignment. To promote cross-linguistic generalisation, we pretrain our model on large-scale sign-text corpora covering British Sign Language (BSL) and American Sign Language (ASL) from the BOBSL and YouTube-SL-25 datasets. With this multilingual pretraining and strong model design, we achieve state-of-the-art results on the challenging BOBSL (BSL) dataset for both SLT and SSA. Our model also demonstrates robust zero-shot generalisation and finetuned SLT performance on How2Sign (ASL), highlighting the potential of scalable translation across different sign languages.
title Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.08040