<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2019-multi-grained">
    <titleInfo>
        <title>Multi-grained Attention with Object-level Grounding for Visual Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pingping</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianhui</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuqing</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min</namePart>
        <namePart type="family">Qiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yong</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Anna</namePart>
            <namePart type="family">Korhonen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Traum</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lluís</namePart>
            <namePart type="family">Màrquez</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Florence, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Attention mechanisms are widely used in Visual Question Answering (VQA) to search for visual clues related to the question. Most approaches train attention models from a coarse-grained association between sentences and images, which tends to fail on small objects or uncommon concepts. To address this problem, this paper proposes a multi-grained attention method. It learns explicit word-object correspondence by two types of word-level attention complementary to the sentence-image association. Evaluated on the VQA benchmark, the multi-grained attention model achieves competitive performance with state-of-the-art models. And the visualized attention maps demonstrate that addition of object-level groundings leads to a better understanding of the images and locates the attended objects more precisely.</abstract>
    <identifier type="citekey">huang-etal-2019-multi-grained</identifier>
    <identifier type="doi">10.18653/v1/P19-1349</identifier>
    <location>
        <url>https://aclanthology.org/P19-1349</url>
    </location>
    <part>
        <date>2019-07</date>
        <extent unit="page">
            <start>3595</start>
            <end>3600</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-grained Attention with Object-level Grounding for Visual Question Answering
%A Huang, Pingping
%A Huang, Jianhui
%A Guo, Yuqing
%A Qiao, Min
%A Zhu, Yong
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F huang-etal-2019-multi-grained
%X Attention mechanisms are widely used in Visual Question Answering (VQA) to search for visual clues related to the question. Most approaches train attention models from a coarse-grained association between sentences and images, which tends to fail on small objects or uncommon concepts. To address this problem, this paper proposes a multi-grained attention method. It learns explicit word-object correspondence by two types of word-level attention complementary to the sentence-image association. Evaluated on the VQA benchmark, the multi-grained attention model achieves competitive performance with state-of-the-art models. And the visualized attention maps demonstrate that addition of object-level groundings leads to a better understanding of the images and locates the attended objects more precisely.
%R 10.18653/v1/P19-1349
%U https://aclanthology.org/P19-1349
%U https://doi.org/10.18653/v1/P19-1349
%P 3595-3600

Markdown (Informal)

[Multi-grained Attention with Object-level Grounding for Visual Question Answering](https://aclanthology.org/P19-1349) (Huang et al., ACL 2019)

• Multi-grained Attention with Object-level Grounding for Visual Question Answering (Huang et al., ACL 2019)

ACL

• Pingping Huang, Jianhui Huang, Yuqing Guo, Min Qiao, and Yong Zhu. 2019. Multi-grained Attention with Object-level Grounding for Visual Question Answering. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3595–3600, Florence, Italy. Association for Computational Linguistics.