@inproceedings{nishimura-etal-2020-visual,
title = "Visual Grounding Annotation of Recipe Flow Graph",
author = "Nishimura, Taichi and
Tomori, Suzushi and
Hashimoto, Hayato and
Hashimoto, Atsushi and
Yamakata, Yoko and
Harashima, Jun and
Ushiku, Yoshitaka and
Mori, Shinsuke",
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
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.527/",
pages = "4275--4284",
language = "eng",
ISBN = "979-10-95546-34-4",
abstract = "In this paper, we provide a dataset that gives visual grounding annotations to recipe flow graphs. A recipe flow graph is a representation of the cooking workflow, which is designed with the aim of understanding the workflow from natural language processing. Such a workflow will increase its value when grounded to real-world activities, and visual grounding is a way to do so. Visual grounding is provided as bounding boxes to image sequences of recipes, and each bounding box is linked to an element of the workflow. Because the workflows are also linked to the text, this annotation gives visual grounding with workflow`s contextual information between procedural text and visual observation in an indirect manner. We subsidiarily annotated two types of event attributes with each bounding box: {\textquotedblleft}doing-the-action,{\textquotedblright} or {\textquotedblleft}done-the-action{\textquotedblright}. As a result of the annotation, we got 2,300 bounding boxes in 272 flow graph recipes. Various experiments showed that the proposed dataset enables us to estimate contextual information described in recipe flow graphs from an image sequence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishimura-etal-2020-visual">
<titleInfo>
<title>Visual Grounding Annotation of Recipe Flow Graph</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taichi</namePart>
<namePart type="family">Nishimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suzushi</namePart>
<namePart type="family">Tomori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hayato</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsushi</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoko</namePart>
<namePart type="family">Yamakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Harashima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshitaka</namePart>
<namePart type="family">Ushiku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinsuke</namePart>
<namePart type="family">Mori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth 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">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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In this paper, we provide a dataset that gives visual grounding annotations to recipe flow graphs. A recipe flow graph is a representation of the cooking workflow, which is designed with the aim of understanding the workflow from natural language processing. Such a workflow will increase its value when grounded to real-world activities, and visual grounding is a way to do so. Visual grounding is provided as bounding boxes to image sequences of recipes, and each bounding box is linked to an element of the workflow. Because the workflows are also linked to the text, this annotation gives visual grounding with workflow‘s contextual information between procedural text and visual observation in an indirect manner. We subsidiarily annotated two types of event attributes with each bounding box: “doing-the-action,” or “done-the-action”. As a result of the annotation, we got 2,300 bounding boxes in 272 flow graph recipes. Various experiments showed that the proposed dataset enables us to estimate contextual information described in recipe flow graphs from an image sequence.</abstract>
<identifier type="citekey">nishimura-etal-2020-visual</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.527/</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>4275</start>
<end>4284</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visual Grounding Annotation of Recipe Flow Graph
%A Nishimura, Taichi
%A Tomori, Suzushi
%A Hashimoto, Hayato
%A Hashimoto, Atsushi
%A Yamakata, Yoko
%A Harashima, Jun
%A Ushiku, Yoshitaka
%A Mori, Shinsuke
%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 Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G eng
%F nishimura-etal-2020-visual
%X In this paper, we provide a dataset that gives visual grounding annotations to recipe flow graphs. A recipe flow graph is a representation of the cooking workflow, which is designed with the aim of understanding the workflow from natural language processing. Such a workflow will increase its value when grounded to real-world activities, and visual grounding is a way to do so. Visual grounding is provided as bounding boxes to image sequences of recipes, and each bounding box is linked to an element of the workflow. Because the workflows are also linked to the text, this annotation gives visual grounding with workflow‘s contextual information between procedural text and visual observation in an indirect manner. We subsidiarily annotated two types of event attributes with each bounding box: “doing-the-action,” or “done-the-action”. As a result of the annotation, we got 2,300 bounding boxes in 272 flow graph recipes. Various experiments showed that the proposed dataset enables us to estimate contextual information described in recipe flow graphs from an image sequence.
%U https://aclanthology.org/2020.lrec-1.527/
%P 4275-4284
Markdown (Informal)
[Visual Grounding Annotation of Recipe Flow Graph](https://aclanthology.org/2020.lrec-1.527/) (Nishimura et al., LREC 2020)
ACL
- Taichi Nishimura, Suzushi Tomori, Hayato Hashimoto, Atsushi Hashimoto, Yoko Yamakata, Jun Harashima, Yoshitaka Ushiku, and Shinsuke Mori. 2020. Visual Grounding Annotation of Recipe Flow Graph. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 4275–4284, Marseille, France. European Language Resources Association.