Representing Signs as Signs: One-Shot ISLR to Facilitate Functional Sign Language Technologies
This work addresses the need for scalable and adaptable sign language technologies, co-created with the Deaf and Hard of Hearing community, though it is incremental in improving generalization over existing methods.
The paper tackles the problem of isolated sign language recognition (ISLR) by proposing a one-shot learning approach that generalizes across languages and evolving vocabularies, achieving state-of-the-art results including 50.8% one-shot MRR on a large dictionary of 10,235 unique signs from a different language than the training set.
Isolated Sign Language Recognition (ISLR) is crucial for scalable sign language technology, yet language-specific approaches limit current models. To address this, we propose a one-shot learning approach that generalises across languages and evolving vocabularies. Our method involves pretraining a model to embed signs based on essential features and using a dense vector search for rapid, accurate recognition of unseen signs. We achieve state-of-the-art results, including 50.8% one-shot MRR on a large dictionary containing 10,235 unique signs from a different language than the training set. Our approach is robust across languages and support sets, offering a scalable, adaptable solution for ISLR. Co-created with the Deaf and Hard of Hearing (DHH) community, this method aligns with real-world needs, and advances scalable sign language recognition.