@inproceedings{paggio-etal-2020-automatic,
title = "Automatic Detection and Classification of Head Movements in Face-to-Face Conversations",
author = "Paggio, Patrizia and
Agirrezabal, Manex and
Jongejan, Bart and
Navarretta, Costanza",
editor = "Paggio, Patrizia and
Gatt, Albert and
Klinger, Roman",
booktitle = "Proceedings of LREC2020 Workshop ``People in language, vision and the mind'' (ONION2020)",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.onion-1.3",
pages = "15--21",
abstract = "This paper presents an approach to automatic head movement detection and classification in data from a corpus of video-recorded face-to-face conversations in Danish involving 12 different speakers. A number of classifiers were trained with different combinations of visual, acoustic and word features and tested in a leave-one-out cross validation scenario. The visual movement features were extracted from the raw video data using OpenPose, and the acoustic ones using Praat. The best results were obtained by a Multilayer Perceptron classifier, which reached an average 0.68 F1 score across the 12 speakers for head movement detection, and 0.40 for head movement classification given four different classes. In both cases, the classifier outperformed a simple most frequent class baseline as well as a more advanced baseline only relying on velocity features.",
language = "English",
ISBN = "979-10-95546-70-2",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="paggio-etal-2020-automatic">
<titleInfo>
<title>Automatic Detection and Classification of Head Movements in Face-to-Face Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manex</namePart>
<namePart type="family">Agirrezabal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Jongejan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Costanza</namePart>
<namePart type="family">Navarretta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of LREC2020 Workshop “People in language, vision and the mind” (ONION2020)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Gatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-70-2</identifier>
</relatedItem>
<abstract>This paper presents an approach to automatic head movement detection and classification in data from a corpus of video-recorded face-to-face conversations in Danish involving 12 different speakers. A number of classifiers were trained with different combinations of visual, acoustic and word features and tested in a leave-one-out cross validation scenario. The visual movement features were extracted from the raw video data using OpenPose, and the acoustic ones using Praat. The best results were obtained by a Multilayer Perceptron classifier, which reached an average 0.68 F1 score across the 12 speakers for head movement detection, and 0.40 for head movement classification given four different classes. In both cases, the classifier outperformed a simple most frequent class baseline as well as a more advanced baseline only relying on velocity features.</abstract>
<identifier type="citekey">paggio-etal-2020-automatic</identifier>
<location>
<url>https://aclanthology.org/2020.onion-1.3</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>15</start>
<end>21</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Detection and Classification of Head Movements in Face-to-Face Conversations
%A Paggio, Patrizia
%A Agirrezabal, Manex
%A Jongejan, Bart
%A Navarretta, Costanza
%Y Paggio, Patrizia
%Y Gatt, Albert
%Y Klinger, Roman
%S Proceedings of LREC2020 Workshop “People in language, vision and the mind” (ONION2020)
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-70-2
%G English
%F paggio-etal-2020-automatic
%X This paper presents an approach to automatic head movement detection and classification in data from a corpus of video-recorded face-to-face conversations in Danish involving 12 different speakers. A number of classifiers were trained with different combinations of visual, acoustic and word features and tested in a leave-one-out cross validation scenario. The visual movement features were extracted from the raw video data using OpenPose, and the acoustic ones using Praat. The best results were obtained by a Multilayer Perceptron classifier, which reached an average 0.68 F1 score across the 12 speakers for head movement detection, and 0.40 for head movement classification given four different classes. In both cases, the classifier outperformed a simple most frequent class baseline as well as a more advanced baseline only relying on velocity features.
%U https://aclanthology.org/2020.onion-1.3
%P 15-21
Markdown (Informal)
[Automatic Detection and Classification of Head Movements in Face-to-Face Conversations](https://aclanthology.org/2020.onion-1.3) (Paggio et al., ONION 2020)
ACL