Programme Outputs

Research Papers

2026
BackTranslation2. 0--A Linguistically Motivated Metric to Assess Sign Language Production
Oliver Cory, Maksym Ivashechkin, Oline Ranum, Low Jian He, Edward Fish, Anton Pelykh, Karahan Sahin, Ozge Mercanoglu Sincan, Richard Bowden
ECCV 2026 Conference
SIGNET: Motion-Level Knowledge Transfer for Cross-Language Sign Language Translation
Sobhan Asasi, Ozge Mercanoglu Sincan, Richard Bowden
ECCV 2026 Conference
SignSparK: Efficient Multilingual Sign Language Production via Sparse Keyframe Learning
Jianhe Low, Alexandre Symeonidis-Herzig, Maksym Ivashechkin, Ozge Mercanoglu Sincan, Richard Bowden
ECCV 2026 Conference
SignRefine: Adapting Foundational Video Models for Sign Language Generation
Anton Pelykh, Edward Fish, Ozge Mercanoglu Sincan, Richard Bowden
ECCV 2026 Conference
SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation
Marshall Thomas, Edward Fish, Richard Bowden
ECCV 2026 Conference
M3T: Discrete Multi-Modal Motion Tokens for Sign Language Production
Alexandre Symeonidis-Herzig, Jianhe Low, Ozge Mercanoglu Sincan, Richard Bowden
BMVC 2026 Conference
2025
Gloss-free sign language translation: An unbiased evaluation of progress in the field
Ozge Mercanoglu Sincan, Jian He Low, Sobhan Asasi, Richard Bowden
CVIU 2025 Journal
VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis
Alexandre Symeonidis-Herzig, Ozge Mercanoglu Sincan, Richard Bowden
ICCVW 2025 Workshop
Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
Edward Fish, Richard Bowden
Neurips 2025 Conference
Vallr: Visual asr language model for lip reading
Marshall Thomas, Edward Fish, Richard Bowden
ICCV 2025 Conference
Signrep: Enhancing self-supervised sign representations
Ryan Wong, Necati Cihan Camgoz, Richard Bowden
ICCV 2025 Conference
Spotter+GPT: Turning Sign Spottings into Sentences with LLMs
Ozge Mercanoglu Sincan, Richard Bowden
IVA 2025 Workshop
Contrastive Pretraining with Dual Visual Encoders for Gloss-Free Sign Language Translation
Ozge Mercanoglu Sincan, Richard Bowden
IVA 2025 Workshop
Hierarchical feature alignment for gloss-free sign language translation
Sobhan Asasi, Mohamed Ilyes Lakhal, Richard Bowden
IVA 2025 Workshop
Sign Spotting Disambiguation using Large Language Models
Low Jian He, Ozge Mercanoglu Sincan, Richard Bowden
IVA 2025 Workshop
Using sign language production as data augmentation to enhance sign language translation
Harry Walsh, Maksym Ivashechkin, Richard Bowden
IVA 2025 Workshop
GaussianGAN: Real-Time Photorealistic controllable Human Avatars
Mohamed Ilyes Lakhal, Richard Bowden
FG 2025 Conference
HandOcc: NeRF-based Hand Rendering with Occupancy Networks
Maksym Ivashechkin, Oscar Mendez, Richard Bowden
FG 2025 Conference
Hands-on: Segmenting individual signs from continuous sequences
Low Jian He, Harry Walsh, Ozge Mercanoglu Sincan, Richard Bowden
FG 2025 Conference
Beyond Gloss: A Hand-Centric Framework for Gloss-Free Sign Language Translation
Sobhan Asasi, Mohamed Ilyas Lakhal, Ozge Mercanoglu Sincan, Richard Bowden
BMVC 2025 Conference
HuGeDiff: 3D Human Generation via Diffusion with Gaussian Splatting
Maksym Ivashechkin, Oscar Mendez, Richard Bowden
BMVC 2025 Conference
SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work
Harry Walsh, Ed Fish, Ozge Mercanoglu Sincan, Mohamed Ilyes Lakhal, Richard Bowden, Neil Fox, Bencie Woll, et al
CVPRW 2025 Workshop
Handling the Details: A Two-Stage Diffusion Approach to Improving Hands in Human Image Generation
Anton Pelykh, Ozge Mercanoglu Sincan, Richard Bowden
IEEE T-BIOM 2025 Journal
SAGE: Segment-Aware Gloss-Free Encoding for Token-Efficient Sign Language Translation
Jian He Low, Ozge Mercanoglu Sincan, Richard Bowden
ICCVW 2025 Workshop
SignGPT Programme Papers — Forthcoming

Programme papers from the core SignGPT grant are currently under development and will appear here as they are accepted. Check the official publications page or Google Scholar for the latest updates.

Acknowledging the Programme

If you use code, data, or findings from the SignGPT programme in your research, please acknowledge the EPSRC Programme Grant and cite the relevant paper(s). The general programme citation is:

BibTeX
@misc{signgpt2025,
  author       = {Bowden, Richard and Zisserman, Andrew and
                  Cormier, Kearsy and Woll, Bencie},
  title        = {{SignGPT}: Building Generative Predictive Transformers
                  for Sign Language},
  year         = {2025},
  note         = {EPSRC Programme Grant 2025--2030},
  institution  = {University of Surrey, University of Oxford, UCL DCAL},
  url          = {https://sites.google.com/view/signgpt/home}
}