@inproceedings{dafnis-etal-2022-bidirectional,
title = "Bidirectional Skeleton-Based Isolated Sign Recognition using Graph Convolutional Networks",
author = "Dafnis, Konstantinos M. and
Chroni, Evgenia and
Neidle, Carol and
Metaxas, Dimitri",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.797",
pages = "7328--7338",
abstract = "To improve computer-based recognition from video of isolated signs from American Sign Language (ASL), we propose a new skeleton-based method that involves explicit detection of the start and end frames of signs, trained on the ASLLVD dataset; it uses linguistically relevant parameters based on the skeleton input. Our method employs a bidirectional learning approach within a Graph Convolutional Network (GCN) framework. We apply this method to the WLASL dataset, but with corrections to the gloss labeling to ensure consistency in the labels assigned to different signs; it is important to have a 1-1 correspondence between signs and text-based gloss labels. We achieve a success rate of 77.43{\%} for top-1 and 94.54{\%} for top-5 using this modified WLASL dataset. Our method, which does not require multi-modal data input, outperforms other state-of-the-art approaches on the same modified WLASL dataset, demonstrating the importance of both attention to the start and end frames of signs and the use of bidirectional data streams in the GCNs for isolated sign recognition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dafnis-etal-2022-bidirectional">
<titleInfo>
<title>Bidirectional Skeleton-Based Isolated Sign Recognition using Graph Convolutional Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Konstantinos</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Dafnis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgenia</namePart>
<namePart type="family">Chroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carol</namePart>
<namePart type="family">Neidle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitri</namePart>
<namePart type="family">Metaxas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To improve computer-based recognition from video of isolated signs from American Sign Language (ASL), we propose a new skeleton-based method that involves explicit detection of the start and end frames of signs, trained on the ASLLVD dataset; it uses linguistically relevant parameters based on the skeleton input. Our method employs a bidirectional learning approach within a Graph Convolutional Network (GCN) framework. We apply this method to the WLASL dataset, but with corrections to the gloss labeling to ensure consistency in the labels assigned to different signs; it is important to have a 1-1 correspondence between signs and text-based gloss labels. We achieve a success rate of 77.43% for top-1 and 94.54% for top-5 using this modified WLASL dataset. Our method, which does not require multi-modal data input, outperforms other state-of-the-art approaches on the same modified WLASL dataset, demonstrating the importance of both attention to the start and end frames of signs and the use of bidirectional data streams in the GCNs for isolated sign recognition.</abstract>
<identifier type="citekey">dafnis-etal-2022-bidirectional</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.797</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>7328</start>
<end>7338</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bidirectional Skeleton-Based Isolated Sign Recognition using Graph Convolutional Networks
%A Dafnis, Konstantinos M.
%A Chroni, Evgenia
%A Neidle, Carol
%A Metaxas, Dimitri
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F dafnis-etal-2022-bidirectional
%X To improve computer-based recognition from video of isolated signs from American Sign Language (ASL), we propose a new skeleton-based method that involves explicit detection of the start and end frames of signs, trained on the ASLLVD dataset; it uses linguistically relevant parameters based on the skeleton input. Our method employs a bidirectional learning approach within a Graph Convolutional Network (GCN) framework. We apply this method to the WLASL dataset, but with corrections to the gloss labeling to ensure consistency in the labels assigned to different signs; it is important to have a 1-1 correspondence between signs and text-based gloss labels. We achieve a success rate of 77.43% for top-1 and 94.54% for top-5 using this modified WLASL dataset. Our method, which does not require multi-modal data input, outperforms other state-of-the-art approaches on the same modified WLASL dataset, demonstrating the importance of both attention to the start and end frames of signs and the use of bidirectional data streams in the GCNs for isolated sign recognition.
%U https://aclanthology.org/2022.lrec-1.797
%P 7328-7338
Markdown (Informal)
[Bidirectional Skeleton-Based Isolated Sign Recognition using Graph Convolutional Networks](https://aclanthology.org/2022.lrec-1.797) (Dafnis et al., LREC 2022)
ACL