Multi-channel Transformers for Multi-articulatory Sign Language Translation
| العنوان: | Multi-channel Transformers for Multi-articulatory Sign Language Translation |
|---|---|
| المؤلفون: | Necati Cihan Camgoz, Simon Hadfield, Richard Bowden, Oscar Koller |
| المصدر: | Computer Vision – ECCV 2020 Workshops ISBN: 9783030668228 ECCV Workshops (4) |
| بيانات النشر: | Springer International Publishing, 2020. |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | Computer science, Speech recognition, Specific-information, 02 engineering and technology, Sign language, Task (project management), 03 medical and health sciences, 0302 clinical medicine, Asynchronous communication, Face (geometry), 030221 ophthalmology & optometry, 0202 electrical engineering, electronic engineering, information engineering, 020201 artificial intelligence & image processing, Communication channel, Transformer (machine learning model), Sign (mathematics) |
| الوصف: | Sign languages use multiple asynchronous information channels (articulators), not just the hands but also the face and body, which computational approaches often ignore. In this paper we tackle the multiarticulatory sign language translation task and propose a novel multichannel transformer architecture. The proposed architecture allows both the inter and intra contextual relationships between different sign articulators to be modelled within the transformer network itself, while also maintaining channel specific information. We evaluate our approach on the RWTH-PHOENIX-Weather-2014T dataset and report competitive translation performance. Importantly, we overcome the reliance on gloss annotations which underpin other state-of-the-art approaches, thereby removing the need for expensive curated datasets. |
| ردمك: | 978-3-030-66822-8 |
| DOI: | 10.1007/978-3-030-66823-5_18 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_________::79cd72edbf0d0cb785c981118561382a https://doi.org/10.1007/978-3-030-66823-5_18 |
| Rights: | OPEN |
| رقم الانضمام: | edsair.doi...........79cd72edbf0d0cb785c981118561382a |
| قاعدة البيانات: | OpenAIRE |
| ردمك: | 9783030668228 |
|---|---|
| DOI: | 10.1007/978-3-030-66823-5_18 |