ChaLearnLAP SLR Challenge @CVPR 2021 : CVPR’2021 ChaLearn Looking at People RGB and RGBD Sign Language Recognition Challenge
Call For Papers
We cordially invite you to participate in our CVPR 2021 Chalearn Looking at People Large Scale Signer Independent Isolated SLR Challenge and Sign Language Recognition in the Wild Workshop.
CVPR’2021 Large Scale Signer Independent Isolated SLR Challenge: http://chalearnlap.cvc.uab.es/challenge/43/description/
We are organizing a sign classification challenge on a new dataset, named AUTSL, consisting of 226 sign categories belonging to Turkish Sign Language and 36,302 isolated sign video samples that are performed by 43 different signers. The dataset includes a variety of different backgrounds from indoor and outdoor environments, lighting variability, different postures of signers, dynamic backgrounds, high intra and low inter-class variabilities. Two competition tracks will be available: RGB only, and RGB+Depth classification.
The results of the challenge will be presented at the associated CVPR 2021 Chalearn workshop. Participants of the challenge will be also invited to submit a paper to the workshop presenting their solutions.
Important Dates :
Start of the Challenge (development phase): December 22th, 2020
Start of test phase: March 3rd, 2021
End of the Challenge: March 11th, 2021
Release of final results: March 20th, 2021
CVPR’2021 Chalearn LAP Sign Language Recognition in the Wild Workshop
There are several open challenges in Sign Language Recognition to develop useful systems in practice, including signer independent evaluation, continuous sign recognition, exploitation of hand contextual cues (face and body), sign production, as well as model generalization to different sign languages and demographics, to name a few. In this workshop, we would like to bring together researchers from the related disciplines to discuss the advances and the challenges in this field. In this context, we accept papers addressing the issues related to, but not limited to, these topics:
- Continuous SLR models
- Isolated SLR models in unconstrained settings
- Multi-modal SLR models
- SLR datasets: design considerations, new proposals and analysis of existing datasets.
- SLR production
- Interpretability/explainability of SLR models
- Few shot and unsupervised SLR
- Fairness, accountability, and transparency in SLR
- Lip reading
- Egocentric SLR
Paper submission to the workshop is independent from challenge participation.
Paper Submission: March 28th, 2021
Decisions to Authors: April 10th, 2021
Camera-Ready: April, 16th, 2021
Juergen Gall, Computer Vision Group, Bonn, Germany
Dimitris Metaxas Rutgers, City of New Brunswick, United States of America
Antonis Argyros, University of Crete, Crete, Greece
Richard Bowden, University of Surrey, Guildford, United Kingdom
Natalia Neverova, Facebook AI Research
Bencie Woll, UCL Deafness Cognition and Language Research Centre
Hongdong Li, Australian National University
ORGANIZATION & SPONSORS
Sergio Escalera, Computer Vision Center (UAB) and University of Barcelona, Spain
Hacer Yalim Keles, Ankara University, Turkey
Julio C. S. Jacques Junior, Universitat Oberta de Catalunya (UOC) and Computer Vision Center (CVC/UAB), Spain
Ozge Mercanoglu Sincan, Ankara University, Turkey
This event is sponsored by ChaLearn - http://chalearnlap.cvc.uab.es/
University of Barcelona, Computer Vision Center at Autonomous University of Barcelona, Human Pose Recovery and Behavior Analysis group, and Ankara University, Computer Vision and Machine Learning Group are the co-sponsors of the SLR Challenge.