@inproceedings{karppa-etal-2012-comparing,
title = "Comparing computer vision analysis of signed language video with motion capture recordings",
author = "Karppa, Matti and
Jantunen, Tommi and
Viitaniemi, Ville and
Laaksonen, Jorma and
Burger, Birgitta and
De Weerdt, Danny",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/321_Paper.pdf",
pages = "2421--2425",
abstract = "We consider a non-intrusive computer-vision method for measuring the motion of a person performing natural signing in video recordings. The quality and usefulness of the method is compared to a traditional marker-based motion capture set-up. The accuracy of descriptors extracted from video footage is assessed qualitatively in the context of sign language analysis by examining if the shape of the curves produced by the different means resemble one another in sequences where the shape could be a source of valuable linguistic information. Then, quantitative comparison is performed first by correlating the computer-vision-based descriptors with the variables gathered with the motion capture equipment. Finally, multivariate linear and non-linar regression methods are applied for predicting the motion capture variables based on combinations of computer vision descriptors. The results show that even the simple computer vision method evaluated in this paper can produce promisingly good results for assisting researchers working on sign language analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karppa-etal-2012-comparing">
<titleInfo>
<title>Comparing computer vision analysis of signed language video with motion capture recordings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matti</namePart>
<namePart type="family">Karppa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tommi</namePart>
<namePart type="family">Jantunen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ville</namePart>
<namePart type="family">Viitaniemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorma</namePart>
<namePart type="family">Laaksonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Birgitta</namePart>
<namePart type="family">Burger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danny</namePart>
<namePart type="family">De Weerdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Asuncion</namePart>
<namePart type="family">Moreno</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We consider a non-intrusive computer-vision method for measuring the motion of a person performing natural signing in video recordings. The quality and usefulness of the method is compared to a traditional marker-based motion capture set-up. The accuracy of descriptors extracted from video footage is assessed qualitatively in the context of sign language analysis by examining if the shape of the curves produced by the different means resemble one another in sequences where the shape could be a source of valuable linguistic information. Then, quantitative comparison is performed first by correlating the computer-vision-based descriptors with the variables gathered with the motion capture equipment. Finally, multivariate linear and non-linar regression methods are applied for predicting the motion capture variables based on combinations of computer vision descriptors. The results show that even the simple computer vision method evaluated in this paper can produce promisingly good results for assisting researchers working on sign language analysis.</abstract>
<identifier type="citekey">karppa-etal-2012-comparing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/321_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2421</start>
<end>2425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing computer vision analysis of signed language video with motion capture recordings
%A Karppa, Matti
%A Jantunen, Tommi
%A Viitaniemi, Ville
%A Laaksonen, Jorma
%A Burger, Birgitta
%A De Weerdt, Danny
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F karppa-etal-2012-comparing
%X We consider a non-intrusive computer-vision method for measuring the motion of a person performing natural signing in video recordings. The quality and usefulness of the method is compared to a traditional marker-based motion capture set-up. The accuracy of descriptors extracted from video footage is assessed qualitatively in the context of sign language analysis by examining if the shape of the curves produced by the different means resemble one another in sequences where the shape could be a source of valuable linguistic information. Then, quantitative comparison is performed first by correlating the computer-vision-based descriptors with the variables gathered with the motion capture equipment. Finally, multivariate linear and non-linar regression methods are applied for predicting the motion capture variables based on combinations of computer vision descriptors. The results show that even the simple computer vision method evaluated in this paper can produce promisingly good results for assisting researchers working on sign language analysis.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/321_Paper.pdf
%P 2421-2425
Markdown (Informal)
[Comparing computer vision analysis of signed language video with motion capture recordings](http://www.lrec-conf.org/proceedings/lrec2012/pdf/321_Paper.pdf) (Karppa et al., LREC 2012)
ACL