ISLR101: an Iranian Word-Level Sign Language Recognition Dataset
This provides a resource for researchers working on under-resourced sign languages, specifically Iranian Sign Language, but is incremental as it focuses on dataset creation rather than novel methods.
The authors tackled the lack of sign language data by introducing ISLR101, the first publicly available Iranian Sign Language dataset for isolated sign language recognition, which includes 4,614 videos covering 101 signs and achieved baseline model accuracies of 97.01% and 94.02% on the test set.
Sign language recognition involves modeling complex multichannel information, such as hand shapes and movements while relying on sufficient sign language-specific data. However, sign languages are often under-resourced, posing a significant challenge for research and development in this field. To address this gap, we introduce ISLR101, the first publicly available Iranian Sign Language dataset for isolated sign language recognition. This comprehensive dataset includes 4,614 videos covering 101 distinct signs, recorded by 10 different signers (3 deaf individuals, 2 sign language interpreters, and 5 L2 learners) against varied backgrounds, with a resolution of 800x600 pixels and a frame rate of 25 frames per second. It also includes skeleton pose information extracted using OpenPose. We establish both a visual appearance-based and a skeleton-based framework as baseline models, thoroughly training and evaluating them on ISLR101. These models achieve 97.01% and 94.02% accuracy on the test set, respectively. Additionally, we publish the train, validation, and test splits to facilitate fair comparisons.