Neural Sign Language Synthesis: Words Are Our Glosses

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F20%3A43959826" target="_blank" >RIV/49777513:23520/20:43959826 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9093516" target="_blank" >https://ieeexplore.ieee.org/document/9093516</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACV45572.2020.9093516" target="_blank" >10.1109/WACV45572.2020.9093516</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Neural Sign Language Synthesis: Words Are Our Glosses

Popis výsledku v původním jazyce

This paper deals with a text-to-video sign language synthesis. Instead of direct video production, we focused on skeletal models production. Our main goal in this paper was to design a fully end-to-end automatic sign language synthesis system trained only on available free data (daily TV broadcasting). Thus, we excluded any manual video annotation. Furthermore, our designed approach even do not rely on any video segmentation. A proposed feed-forward transformer and recurrent transformer were investigated. To improve the performance of our sequence-to-sequence transformer, soft non-monotonic attention was employed in our training process. A benefit of character-level features was compared with word-level features. We focused our experiments on a weather forecasting dataset in the Czech Sign Language.

Název v anglickém jazyce

Neural Sign Language Synthesis: Words Are Our Glosses

Popis výsledku anglicky

This paper deals with a text-to-video sign language synthesis. Instead of direct video production, we focused on skeletal models production. Our main goal in this paper was to design a fully end-to-end automatic sign language synthesis system trained only on available free data (daily TV broadcasting). Thus, we excluded any manual video annotation. Furthermore, our designed approach even do not rely on any video segmentation. A proposed feed-forward transformer and recurrent transformer were investigated. To improve the performance of our sequence-to-sequence transformer, soft non-monotonic attention was employed in our training process. A benefit of character-level features was compared with word-level features. We focused our experiments on a weather forecasting dataset in the Czech Sign Language.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/EF15_003%2F0000466" target="_blank" >EF15_003/0000466: Umělá inteligence a uvažování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2020 IEEE Winter Conference on Applications of Computer Vision (WACV)

ISBN

978-1-72816-553-0

ISSN

2472-6737

e-ISSN

2642-9381

Počet stran výsledku

9

Strana od-do

3384-3392

Název nakladatele

IEEE

Místo vydání

USA

Místo konání akce

Snowmass Village, CO, USA (385)

Datum konání akce

1. 3. 2020

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000578444803049