@inproceedings{conser-etal-2019-revisiting,
title = "Revisiting Visual Grounding",
author = "Conser, Erik and
Hahn, Kennedy and
Watson, Chandler and
Mitchell, Melanie",
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/W19-1804",
doi = "10.18653/v1/W19-1804",
pages = "37--46",
abstract = "We revisit a particular visual grounding method: the {``}Image Retrieval Using Scene Graphs{''} (IRSG) system of Johnson et al. Our experiments indicate that the system does not effectively use its learned object-relationship models. We also look closely at the IRSG dataset, as well as the widely used Visual Relationship Dataset (VRD) that is adapted from it. We find that these datasets exhibit bias that allows methods that ignore relationships to perform relatively well. We also describe several other problems with the IRSG dataset, and report on experiments using a subset of the dataset in which the biases and other problems are removed. Our studies contribute to a more general effort: that of better understanding what machine-learning methods that combine language and vision actually learn and what popular datasets actually test.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="conser-etal-2019-revisiting">
<titleInfo>
<title>Revisiting Visual Grounding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Conser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kennedy</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chandler</namePart>
<namePart type="family">Watson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melanie</namePart>
<namePart type="family">Mitchell</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>We revisit a particular visual grounding method: the “Image Retrieval Using Scene Graphs” (IRSG) system of Johnson et al. Our experiments indicate that the system does not effectively use its learned object-relationship models. We also look closely at the IRSG dataset, as well as the widely used Visual Relationship Dataset (VRD) that is adapted from it. We find that these datasets exhibit bias that allows methods that ignore relationships to perform relatively well. We also describe several other problems with the IRSG dataset, and report on experiments using a subset of the dataset in which the biases and other problems are removed. Our studies contribute to a more general effort: that of better understanding what machine-learning methods that combine language and vision actually learn and what popular datasets actually test.</abstract>
<identifier type="citekey">conser-etal-2019-revisiting</identifier>
<identifier type="doi">10.18653/v1/W19-1804</identifier>
<location>
<url>https://aclanthology.org/W19-1804</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>37</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Revisiting Visual Grounding
%A Conser, Erik
%A Hahn, Kennedy
%A Watson, Chandler
%A Mitchell, Melanie
%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 conser-etal-2019-revisiting
%X We revisit a particular visual grounding method: the “Image Retrieval Using Scene Graphs” (IRSG) system of Johnson et al. Our experiments indicate that the system does not effectively use its learned object-relationship models. We also look closely at the IRSG dataset, as well as the widely used Visual Relationship Dataset (VRD) that is adapted from it. We find that these datasets exhibit bias that allows methods that ignore relationships to perform relatively well. We also describe several other problems with the IRSG dataset, and report on experiments using a subset of the dataset in which the biases and other problems are removed. Our studies contribute to a more general effort: that of better understanding what machine-learning methods that combine language and vision actually learn and what popular datasets actually test.
%R 10.18653/v1/W19-1804
%U https://aclanthology.org/W19-1804
%U https://doi.org/10.18653/v1/W19-1804
%P 37-46
Markdown (Informal)
[Revisiting Visual Grounding](https://aclanthology.org/W19-1804) (Conser et al., NAACL 2019)
ACL
- Erik Conser, Kennedy Hahn, Chandler Watson, and Melanie Mitchell. 2019. Revisiting Visual Grounding. In Proceedings of the Second Workshop on Shortcomings in Vision and Language, pages 37–46, Minneapolis, Minnesota. Association for Computational Linguistics.