Workshop description


Summary

Sign Language Recognition (SLR) systems have considerably improved their performance in recent years. However, several open challenges still need to be solved in order to allow SLR to be useful in practice, including continuous sign recognition and model generalization to different sign languages and demographics, among others. There is also an increased demand for interdisciplinary collaboration, including the deaf community. In line with these, we would like to bring together researchers in the field and from related disciplines to discuss the advances and new challenges on the topic of SLR. To advance and motivate the research on the field, this workshop will have an associated challenge. It will use a partially annotated continuous sign language dataset of more than 10 hours of video data in the health domain and will address the challenging problem of fine-grain sign spotting for continuous SLR. In this context, we want to put a spotlight on the strengths and limitations of the existing approaches, and define the future directions of the field.

Topics and Motivation

SLR is an active area in computer vision that used to be categorized into isolated (ISLR) and continuous (CSLR) settings. Sign spotting is a research field related to both ISLR and CSLR, with applicability by itself (e.g., search and retrieval in SL content), and as a previous step in preparing and collecting footage for CSLR. In line with these, we would like to bring together researchers in the field and from related disciplines (e.g. linguistics, human computer interaction, etc.) to discuss the advances and new challenges to address in SLR in unconstrained settings. We want to put a spotlight to the strengths and limitations of the existing approaches, and define the future directions of the field. In this context, we accept papers addressing the issues related, but not limited, to:

  • Techniques for preprocessing RGB and RGB-D streams for SLR;
  • Models for ISLR and CSLR;
  • Sign Spotting systems and performance;
  • Sign Spotting for feeding CSLR systems;
  • Transfer learning, few shot and unsupervised systems for SLR;
  • Multi-modal learning and impact in ISLR and CSLR.

Important Dates and Submission Instructions

Detailed information about the important dates and submission instructions can be found here.

Invited Speakers

Andrew Zissermann

Annelies Braffort

Lale Akarun

Richard Bowden

 

Associated Challenge

Check our associated ECCV'2022 ChaLearn Looking at People Sign Spotting Challenge.

 

 

News


There are no news registered in