Sign Pose-based Transformer for Word-level Sign Language Recognition

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F22%3A43966109" target="_blank" >RIV/49777513:23520/22:43966109 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/9707552" target="_blank" >https://ieeexplore.ieee.org/document/9707552</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WACVW54805.2022.00024" target="_blank" >10.1109/WACVW54805.2022.00024</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Sign Pose-based Transformer for Word-level Sign Language Recognition

Popis výsledku v původním jazyce

In this paper we present a system for word-level sign language recognition based on the Transformer model. We aim at a solution with low computational cost, since we see great potential in the usage of such recognition system on hand-held devices. We base the recognition on the estimation of the pose of the human body in the form of 2D landmark locations. We introduce a robust pose normalization scheme which takes the signing space in consideration and processes the hand poses in a separate local coordinate system, independent on the body pose. We show experimentally the significant impact of this normalization on the accuracy of our proposed system. We introduce several augmentations of the body pose that further improve the accuracy, including a novel sequential joint rotation augmentation. With all the systems in place, we achieve state of the art top-1 results on the WLASL and LSA64 datasets. For WLASL, we are able to successfully recognize 63.18 % of sign recordings in the 100-gloss subset, which is a relative improvement of 5 % from the prior state of the art. For the 300-gloss subset, we achieve recognition rate of 43.78 % which is a relative improvement of 3.8 %. With the LSA64 dataset, we report test recognition accuracy of 100 %.

Název v anglickém jazyce

Sign Pose-based Transformer for Word-level Sign Language Recognition

Popis výsledku anglicky

In this paper we present a system for word-level sign language recognition based on the Transformer model. We aim at a solution with low computational cost, since we see great potential in the usage of such recognition system on hand-held devices. We base the recognition on the estimation of the pose of the human body in the form of 2D landmark locations. We introduce a robust pose normalization scheme which takes the signing space in consideration and processes the hand poses in a separate local coordinate system, independent on the body pose. We show experimentally the significant impact of this normalization on the accuracy of our proposed system. We introduce several augmentations of the body pose that further improve the accuracy, including a novel sequential joint rotation augmentation. With all the systems in place, we achieve state of the art top-1 results on the WLASL and LSA64 datasets. For WLASL, we are able to successfully recognize 63.18 % of sign recordings in the 100-gloss subset, which is a relative improvement of 5 % from the prior state of the art. For the 300-gloss subset, we achieve recognition rate of 43.78 % which is a relative improvement of 3.8 %. With the LSA64 dataset, we report test recognition accuracy of 100 %.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20205 - Automation and control systems

Projekt

<a href="/cs/project/LM2018101" target="_blank" >LM2018101: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy</a><br>

Návaznosti

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

Rok uplatnění

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops

ISBN

978-1-66545-824-5

ISSN

2572-4398

e-ISSN

2690-621X

Počet stran výsledku

10

Strana od-do

182-191

Název nakladatele

IEEE

Místo vydání

New York

Místo konání akce

Waikoloa, HI, Spojené státy

Datum konání akce

4. 1. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000802187100020