A Comprehensive Study on Deep Learning-based Methods for Sign Language Recognition
It addresses sign language recognition for accessibility, but is largely incremental with dataset creation and method adaptation.
This paper tackles sign language recognition by comparing deep learning methods on multiple datasets, introducing two sequence training criteria from other fields and creating a new Greek sign language dataset with sentence-level annotations.
In this paper, a comparative experimental assessment of computer vision-based methods for sign language recognition is conducted. By implementing the most recent deep neural network methods in this field, a thorough evaluation on multiple publicly available datasets is performed. The aim of the present study is to provide insights on sign language recognition, focusing on mapping non-segmented video streams to glosses. For this task, two new sequence training criteria, known from the fields of speech and scene text recognition, are introduced. Furthermore, a plethora of pretraining schemes is thoroughly discussed. Finally, a new RGB+D dataset for the Greek sign language is created. To the best of our knowledge, this is the first sign language dataset where sentence and gloss level annotations are provided for a video capture.