SLRTP @CVPR 2025
Schedule
Accessibility and Interpretation
Our workshop will be hybrid, with both in-person and remote participation options. Workshop languages are American Sign Language (ASL), International Sign (IS), and English.
ASL/English interpretation will be provided on-site for the whole workshop. IS/English interpretation will be provided remotely for stage presentations. If you would like IS/English interpreting for the poster session as well, please contact us at o.mercanoglusincan@surrey.ac.uk by April 4, 2025.
We sincerely thank CVPR for providing interpretation services and supporting accessibility at our workshop.
Registration & Welcome

Keynote 1 - Michael Black
3D human pose and shape estimation from video for sign language and moreMichael Black is an Honorary Professor at the University of Tübingen and a founding director at the Max Planck Institute for Intelligent Systems. He is renowned for his pioneering work in human motion generation. His research focuses on creating highly realistic digital human models that capture intricate motion details. His work has won several awards including the IEEE Computer Society Outstanding Paper Award (1991), Honorable Mention for the Marr Prize (1999 and 2005), the 2010 Koenderink Prize for Fundamental Contributions in Computer Vision, and one of the ICCV 2013 Helmholtz Prizes. He is a foreign member of the Royal Swedish Academy of Sciences. In 2013 he co-founded Body Labs Inc., which was acquired by Amazon in 2017.

Keynote 2 - Maartje De Meulder
SoonMaartje De Meulder is a Senior Researcher at HU – University of Applied Sciences Utrecht and also an Honorary Research Fellow at SIGNS@HWU at Heriot-Watt University. Her research addresses the ethical, social, and cultural aspects of sign technology, ensuring that the development of such technologies respects and supports Deaf communities. Her work has been published in a range of different journals such as Language Policy, Applied Linguistics Review, The Journal of Multilingual and Multicultural Development, Human Rights Quarterly, and Translation and Interpreting Studies. She has co-edited Innovations in Deaf Studies (Oxford University Press, 2017) and The Legal Recognition of Sign Languages (Multilingual Matters, 2019), and has been a guest editor of several special issues of journals.
Oral Presentations
5 min presentation, and Q&A in the poster session. • Exploring Pose-based Sign Language Translation: Ablation Studies and Attention Insights☕️ Coffee Break

Keynote 3 - Matthias Nießner
SoonMatthias Nießner is a Professor at the Technical University of Munich, where he leads the Visual Computing Lab. He leads groundbreaking research in animatable avatars. He conducts research into 3D digitization at the juncture between the fields of computer graphics, computer vision, and artificial intelligence. His research is oriented towards the generation of 3D models of real-world environments using video and range cameras (for example with Deep Learning). Research conducted in the Visual Computing Lab is highly varied and includes conducting analyses to further the semantic understanding of the 3D environments, video-editing and numerical optimization.

Keynote 4 - Abraham Glasser
From Hype to Real-World Solutions: The Interpreting Industry's Collaborative Response to AIAbraham Glasser is an Assistant Professor at Gallaudet University since 2023. He specializes in Deaf interaction design for AI technologies. His research is centered on creating AI systems that are accessible and intuitive for Deaf users, ensuring that the interaction between AI and Deaf individuals is natural and effective. He is the recipient of an Honorable Mention in the 2018 National Science Foundation Graduate Research Fellowship program, and he was the first-place winner in the Student Research Competition at the ACM CHI Conference on Human Factors in Computing Systems.
🏆 Sign Language Production Challenge Winners
• Challenge Overview • Team1: A retrieval-based approach using generated gloss segmentation and pose dictionary lookups for high-fidelity sign generation • Team3: A gloss-free transformer encoder-decoder where poses are generated from latent embeddings❓ Q&A for Remote Papers
Pre-recorded videos of these accepted papers are available. Please watch the pre-recorded presentations before the live session. We will have their Q&A discussions during the live session. • Diffusion-Based Continuous Sign Language Generation with Cluster-Specific Fine-Tuning and Motion-Adapted TransformerVideo • BUTID: A Large-scale Sign Language Translation Dataset and Benchmarks for Turkish Sign LanguageVideoSubtitle • CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language RecognitionVideoSubtitle📌 Poster Session & Networking
Posters will be displayed in Exhibit Hall D. Our workshop's assigned poster boards are #389 - #396.SLP Competition Winners
Accepted Papers
We received 18 submissions, and 5 papers were accepted, resulting in an acceptance rate of approximately 28%.
-
Cross-Modal Consistency Learning for Sign Language Recognition Kepeng Wu, Zecheng Li, Weichao Zhao, Hezhen Hu, Wengang Zhou, Houqiang Li
-
Exploring Pose-based Sign Language Translation: Ablation Studies and Attention Insights Tomáš Železný, Jakub Straka, Václav Javorek, Ondřej Valach, Marek Hrúz, Ivan Gruber
-
Diffusion-Based Continuous Sign Language Generation with Cluster-Specific Fine-Tuning and Motion-Adapted Transformer Razieh Rastgoo, Kourosh Kiani, Sergio Escalera
-
BUTID: A Large-scale Sign Language Translation Dataset and Benchmarks for Turkish Sign Language Karahan Şahin, Lale Akarun, Kadir Gökgöz, Murat Saraçlar
-
CLIP-SLA: Parameter-Efficient CLIP Adaptation for Continuous Sign Language Recognition Sarah Alyami, Hamzah Luqman
-
SLRTP2025 Sign Language Production Challenge: Methodology, Results and Future Work Harry Walsh, Ed Fish, Ozge Mercanoglu Sincan, Mohamed Ilyes Lakhal, Richard Bowden, Neil Fox, Kearsy Cormier, Bencie Woll, Kepeng Wu, Zecheng Li, Weichao Zhao, Haodong Wang, Wengang Zhou, Houqiang Li, Shengeng Tang, Jiayi He, Xu Wang, Ruobei Zhang, Yaxiong Wang, Lechao Cheng, Meryem Tasyurek, Tugce Kiziltepe, Hacer Yalim Keles