@inproceedings{stefanov-beskow-2016-multi,
title = "A Multi-party Multi-modal Dataset for Focus of Visual Attention in Human-human and Human-robot Interaction",
author = "Stefanov, Kalin and
Beskow, Jonas",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1703",
pages = "4440--4444",
abstract = "This papers describes a data collection setup and a newly recorded dataset. The main purpose of this dataset is to explore patterns in the focus of visual attention of humans under three different conditions - two humans involved in task-based interaction with a robot; same two humans involved in task-based interaction where the robot is replaced by a third human, and a free three-party human interaction. The dataset contains two parts - 6 sessions with duration of approximately 3 hours and 9 sessions with duration of approximately 4.5 hours. Both parts of the dataset are rich in modalities and recorded data streams - they include the streams of three Kinect v2 devices (color, depth, infrared, body and face data), three high quality audio streams, three high resolution GoPro video streams, touch data for the task-based interactions and the system state of the robot. In addition, the second part of the dataset introduces the data streams from three Tobii Pro Glasses 2 eye trackers. The language of all interactions is English and all data streams are spatially and temporally aligned.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stefanov-beskow-2016-multi">
<titleInfo>
<title>A Multi-party Multi-modal Dataset for Focus of Visual Attention in Human-human and Human-robot Interaction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalin</namePart>
<namePart type="family">Stefanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Beskow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This papers describes a data collection setup and a newly recorded dataset. The main purpose of this dataset is to explore patterns in the focus of visual attention of humans under three different conditions - two humans involved in task-based interaction with a robot; same two humans involved in task-based interaction where the robot is replaced by a third human, and a free three-party human interaction. The dataset contains two parts - 6 sessions with duration of approximately 3 hours and 9 sessions with duration of approximately 4.5 hours. Both parts of the dataset are rich in modalities and recorded data streams - they include the streams of three Kinect v2 devices (color, depth, infrared, body and face data), three high quality audio streams, three high resolution GoPro video streams, touch data for the task-based interactions and the system state of the robot. In addition, the second part of the dataset introduces the data streams from three Tobii Pro Glasses 2 eye trackers. The language of all interactions is English and all data streams are spatially and temporally aligned.</abstract>
<identifier type="citekey">stefanov-beskow-2016-multi</identifier>
<location>
<url>https://aclanthology.org/L16-1703</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4440</start>
<end>4444</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-party Multi-modal Dataset for Focus of Visual Attention in Human-human and Human-robot Interaction
%A Stefanov, Kalin
%A Beskow, Jonas
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F stefanov-beskow-2016-multi
%X This papers describes a data collection setup and a newly recorded dataset. The main purpose of this dataset is to explore patterns in the focus of visual attention of humans under three different conditions - two humans involved in task-based interaction with a robot; same two humans involved in task-based interaction where the robot is replaced by a third human, and a free three-party human interaction. The dataset contains two parts - 6 sessions with duration of approximately 3 hours and 9 sessions with duration of approximately 4.5 hours. Both parts of the dataset are rich in modalities and recorded data streams - they include the streams of three Kinect v2 devices (color, depth, infrared, body and face data), three high quality audio streams, three high resolution GoPro video streams, touch data for the task-based interactions and the system state of the robot. In addition, the second part of the dataset introduces the data streams from three Tobii Pro Glasses 2 eye trackers. The language of all interactions is English and all data streams are spatially and temporally aligned.
%U https://aclanthology.org/L16-1703
%P 4440-4444
Markdown (Informal)
[A Multi-party Multi-modal Dataset for Focus of Visual Attention in Human-human and Human-robot Interaction](https://aclanthology.org/L16-1703) (Stefanov & Beskow, LREC 2016)
ACL