<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2019-generating">
    <titleInfo>
        <title>Generating Question Relevant Captions to Aid Visual Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jialin</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zeyuan</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Raymond</namePart>
        <namePart type="family">Mooney</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-jul</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We present a novel approach to better VQA performance that exploits this connection by jointly generating captions that are targeted to help answer a specific visual question. The model is trained using an existing caption dataset by automatically determining question-relevant captions using an online gradient-based method. Experimental results on the VQA v2 challenge demonstrates that our approach obtains state-of-the-art VQA performance (e.g. 68.4% in the Test-standard set using a single model) by simultaneously generating question-relevant captions.</abstract>
    <identifier type="citekey">wu-etal-2019-generating</identifier>
    <identifier type="doi">10.18653/v1/P19-1348</identifier>
    <location>
        <url>https://aclanthology.org/P19-1348</url>
    </location>
    <part>
        <date>2019-jul</date>
        <extent unit="page">
            <start>3585</start>
            <end>3594</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Generating Question Relevant Captions to Aid Visual Question Answering
%A Wu, Jialin
%A Hu, Zeyuan
%A Mooney, Raymond
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 jul
%I Association for Computational Linguistics
%C Florence, Italy
%F wu-etal-2019-generating
%X Visual question answering (VQA) and image captioning require a shared body of general knowledge connecting language and vision. We present a novel approach to better VQA performance that exploits this connection by jointly generating captions that are targeted to help answer a specific visual question. The model is trained using an existing caption dataset by automatically determining question-relevant captions using an online gradient-based method. Experimental results on the VQA v2 challenge demonstrates that our approach obtains state-of-the-art VQA performance (e.g. 68.4% in the Test-standard set using a single model) by simultaneously generating question-relevant captions.
%R 10.18653/v1/P19-1348
%U https://aclanthology.org/P19-1348
%U https://doi.org/10.18653/v1/P19-1348
%P 3585-3594