Beyond Gloss: A Hand-Centric Framework for Gloss-Free Sign Language Translation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Asasi, Sobhan, Lakhal, Mohamed Ilyas, Sincan, Ozge Mercanoglu, Bowden, Richard
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912561881939968
author Asasi, Sobhan
Lakhal, Mohamed Ilyas
Sincan, Ozge Mercanoglu
Bowden, Richard
author_facet Asasi, Sobhan
Lakhal, Mohamed Ilyas
Sincan, Ozge Mercanoglu
Bowden, Richard
contents Sign Language Translation (SLT) is a challenging task that requires bridging the modality gap between visual and linguistic information while capturing subtle variations in hand shapes and movements. To address these challenges, we introduce \textbf{BeyondGloss}, a novel gloss-free SLT framework that leverages the spatio-temporal reasoning capabilities of Video Large Language Models (VideoLLMs). Since existing VideoLLMs struggle to model long videos in detail, we propose a novel approach to generate fine-grained, temporally-aware textual descriptions of hand motion. A contrastive alignment module aligns these descriptions with video features during pre-training, encouraging the model to focus on hand-centric temporal dynamics and distinguish signs more effectively. To further enrich hand-specific representations, we distill fine-grained features from HaMeR. Additionally, we apply a contrastive loss between sign video representations and target language embeddings to reduce the modality gap in pre-training. \textbf{BeyondGloss} achieves state-of-the-art performance on the Phoenix14T and CSL-Daily benchmarks, demonstrating the effectiveness of the proposed framework. We will release the code upon acceptance of the paper.
format Preprint
id arxiv_https___arxiv_org_abs_2507_23575
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Gloss: A Hand-Centric Framework for Gloss-Free Sign Language Translation
Asasi, Sobhan
Lakhal, Mohamed Ilyas
Sincan, Ozge Mercanoglu
Bowden, Richard
Computer Vision and Pattern Recognition
Sign Language Translation (SLT) is a challenging task that requires bridging the modality gap between visual and linguistic information while capturing subtle variations in hand shapes and movements. To address these challenges, we introduce \textbf{BeyondGloss}, a novel gloss-free SLT framework that leverages the spatio-temporal reasoning capabilities of Video Large Language Models (VideoLLMs). Since existing VideoLLMs struggle to model long videos in detail, we propose a novel approach to generate fine-grained, temporally-aware textual descriptions of hand motion. A contrastive alignment module aligns these descriptions with video features during pre-training, encouraging the model to focus on hand-centric temporal dynamics and distinguish signs more effectively. To further enrich hand-specific representations, we distill fine-grained features from HaMeR. Additionally, we apply a contrastive loss between sign video representations and target language embeddings to reduce the modality gap in pre-training. \textbf{BeyondGloss} achieves state-of-the-art performance on the Phoenix14T and CSL-Daily benchmarks, demonstrating the effectiveness of the proposed framework. We will release the code upon acceptance of the paper.
title Beyond Gloss: A Hand-Centric Framework for Gloss-Free Sign Language Translation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.23575