@inproceedings{modi-parde-2019-steep,
title = "The Steep Road to Happily Ever after: an Analysis of Current Visual Storytelling Models",
author = "Modi, Yatri and
Parde, Natalie",
editor = "Bernardi, Raffaella and
Fernandez, Raquel and
Gella, Spandana and
Kafle, Kushal and
Kanan, Christopher and
Lee, Stefan and
Nabi, Moin",
booktitle = "Proceedings of the Second Workshop on Shortcomings in Vision and Language",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-1805",
doi = "10.18653/v1/W19-1805",
pages = "47--57",
abstract = "Visual storytelling is an intriguing and complex task that only recently entered the research arena. In this work, we survey relevant work to date, and conduct a thorough error analysis of three very recent approaches to visual storytelling. We categorize and provide examples of common types of errors, and identify key shortcomings in current work. Finally, we make recommendations for addressing these limitations in the future.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="modi-parde-2019-steep">
<titleInfo>
<title>The Steep Road to Happily Ever after: an Analysis of Current Visual Storytelling Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yatri</namePart>
<namePart type="family">Modi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Parde</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Shortcomings in Vision and Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Raffaella</namePart>
<namePart type="family">Bernardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Kafle</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Kanan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moin</namePart>
<namePart type="family">Nabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visual storytelling is an intriguing and complex task that only recently entered the research arena. In this work, we survey relevant work to date, and conduct a thorough error analysis of three very recent approaches to visual storytelling. We categorize and provide examples of common types of errors, and identify key shortcomings in current work. Finally, we make recommendations for addressing these limitations in the future.</abstract>
<identifier type="citekey">modi-parde-2019-steep</identifier>
<identifier type="doi">10.18653/v1/W19-1805</identifier>
<location>
<url>https://aclanthology.org/W19-1805</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>47</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Steep Road to Happily Ever after: an Analysis of Current Visual Storytelling Models
%A Modi, Yatri
%A Parde, Natalie
%Y Bernardi, Raffaella
%Y Fernandez, Raquel
%Y Gella, Spandana
%Y Kafle, Kushal
%Y Kanan, Christopher
%Y Lee, Stefan
%Y Nabi, Moin
%S Proceedings of the Second Workshop on Shortcomings in Vision and Language
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F modi-parde-2019-steep
%X Visual storytelling is an intriguing and complex task that only recently entered the research arena. In this work, we survey relevant work to date, and conduct a thorough error analysis of three very recent approaches to visual storytelling. We categorize and provide examples of common types of errors, and identify key shortcomings in current work. Finally, we make recommendations for addressing these limitations in the future.
%R 10.18653/v1/W19-1805
%U https://aclanthology.org/W19-1805
%U https://doi.org/10.18653/v1/W19-1805
%P 47-57
Markdown (Informal)
[The Steep Road to Happily Ever after: an Analysis of Current Visual Storytelling Models](https://aclanthology.org/W19-1805) (Modi & Parde, NAACL 2019)
ACL