SLRTP

Sign languages are visual languages and a key form of communication for deaf communities. Thanks to recent advances in deep learning and computer vision and the availability of larger datasets, significant progress has been made in sign language technologies. Following the first and second editions, this workshop is motivated by the desire to broaden participation in sign language research from the computer vision community. It aims to bring together researchers working on different aspects of vision-based sign language research and sign language linguists to explore recent advances and future directions in sign language recognition, translation, and production.

Accessibility & Interpretation

For information about ASL and IS interpretation for the workshop, please visit our Schedule page.

Registration

All participants need to register through the official CVPR registration page. Please visit CVPR 2025 Registration for details on pricing and access options.

Keynotes

Michael Black Max Planck Institute for Intelligent Systems

Matthias Nießner Technical University of Munich

Maartje De Meulder HU – University of Applied Sciences Utrecht

Abraham Glasser Gallaudet University

Important Dates:

We invite high-quality research papers to our workshop. For detailed information, please visit our Call for Paper.

Paper Submission: March 16, 2025 (11:59 PM PST)
Decisions to Authors: April 1, 2025 (11:59 PM PST)
Camera-Ready: ~~April 5~~ April 12, 2025 (11:59 PM PST)

We are hosting the first Sign Language Production (SLP) challange to address the growing need for standardized evaluation metrics and representations in SLP research. Check our Sign Language Production Challenge.

Start of the Challenge (development phase): January 13, 2025
Start of test phase: February 24, 2025
End of the Challenge: March 3, 2025
Code and Fact sheets submission: March 7, 2025
Release of results: March 13, 2025

Challenge Results

We are delighted to announce the winners of the SLRTP 2025 Sign Language Production Challenge. This year, more than 30 teams competed, and we thank all participants for their efforts. Below are the top three teams: