Centre for Vision, Speech and Signal Processing  ·  University of Surrey

Making Sign Language
Accessible Through AI & Vision

The CogVis Lab develops vision and language models that understand, translate, and produce sign languages — bridging communication between Deaf and hearing communities through gloss-free translation, avatar-driven production, and LLM-powered annotation.

What we do

Research Areas

We work at the intersection of computer vision, natural language processing, and accessibility to build systems that understand and generate sign languages.

01
Sign Language Translation

Gloss-free, end-to-end translation of continuous sign language video into spoken language text using visual transformers and large language models.

02
Sign Language Production

Generating natural, diverse sign language video from spoken text via motion tokenisation, sparse keyframe learning, and photorealistic avatar synthesis.

03
Sign Spotting & Recognition

Detecting and disambiguating individual signs in unconstrained continuous video, including fingerspelling and rare or out-of-vocabulary signs.

04
LLMs & Agentic Methods

Leveraging agentic large language models for linguistically grounded sign annotation, dataset curation, and multilingual sign language understanding.

Selected work

Recent Publications

We publish at top venues in computer vision and machine learning. See all on Google Scholar →

Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
E Fish, R Bowden
NeurIPS 2025
Gloss-Free Sign Language Translation: An Unbiased Evaluation of Progress in the Field
O Mercanoglu Sincan, JH Low, S Asasi, R Bowden
CVIU 2025
SignAgent: Agentic LLMs for Linguistically-Grounded Sign Language Annotation and Dataset Curation
O Cory, OM Sincan, R Bowden
arXiv 2026
M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production
A Symeonidis-Herzig, J Low, OM Sincan, R Bowden
arXiv 2026
SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning
J Low, A Symeonidis-Herzig, M Ivashechkin, OM Sincan, R Bowden
arXiv 2026
Latest updates

News

Mar 2026

Harry Walsh and Ryan Wong has graduated with PhDs! Congratulations to Harry and Ryan on successfully defending their theses and earning their doctorates.

Dec 2025

SignGPT project launched! We are excited to announce the launch of SignGPT, our new initiative focused on leveraging large language models for sign language understanding and generation. Stay tuned for updates on our research and developments in this area.