@inproceedings{wang-etal-2021-li,
title = "利用图像描述与知识图谱增强表示的视觉问答(Exploiting Image Captions and External Knowledge as Representation Enhancement for Visual Question Answering)",
author = "Wang, Gechao and
Zhu, Muhua and
Xu, Chen and
Zhang, Yan and
Wang, Huizhen and
Zhu, Jingbo",
editor = "Li, Sheng and
Sun, Maosong and
Liu, Yang and
Wu, Hua and
Liu, Kang and
Che, Wanxiang and
He, Shizhu and
Rao, Gaoqi",
booktitle = "Proceedings of the 20th Chinese National Conference on Computational Linguistics",
month = aug,
year = "2021",
address = "Huhhot, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2021.ccl-1.30",
pages = "316--326",
abstract = "视觉问答作为多模态任务,需要深度理解图像和文本问题从而推理出答案。然而在许多情况下,仅在图像和问题上进行简单推理难以得到正确的答案,事实上还有其它有效的信息可以被利用,例如图像描述、外部知识等。针对以上问题,本文提出了利用图像描述和外部知识增强表示的视觉问答模型。该模型以问题为导向,基于协同注意力机制分别在图像和其描述上进行编码,并且利用知识图谱嵌入,将外部知识编码到模型当中,丰富了模型的特征表示,增强模型的推理能力。在OKVQA数据集上的实验结果表明本文方法相比基线系统有1.71{\%}的准确率提升,与先前工作中的主流模型相比也有1.88{\%}的准确率提升,证明了本文方法的有效性。",
language = "Chinese",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-li">
<titleInfo>
<title>利用图像描述与知识图谱增强表示的视觉问答(Exploiting Image Captions and External Knowledge as Representation Enhancement for Visual Question Answering)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gechao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhua</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huizhen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">Chinese</languageTerm>
<languageTerm type="code" authority="iso639-2b">chi</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhu</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaoqi</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Huhhot, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>视觉问答作为多模态任务,需要深度理解图像和文本问题从而推理出答案。然而在许多情况下,仅在图像和问题上进行简单推理难以得到正确的答案,事实上还有其它有效的信息可以被利用,例如图像描述、外部知识等。针对以上问题,本文提出了利用图像描述和外部知识增强表示的视觉问答模型。该模型以问题为导向,基于协同注意力机制分别在图像和其描述上进行编码,并且利用知识图谱嵌入,将外部知识编码到模型当中,丰富了模型的特征表示,增强模型的推理能力。在OKVQA数据集上的实验结果表明本文方法相比基线系统有1.71%的准确率提升,与先前工作中的主流模型相比也有1.88%的准确率提升,证明了本文方法的有效性。</abstract>
<identifier type="citekey">wang-etal-2021-li</identifier>
<location>
<url>https://aclanthology.org/2021.ccl-1.30</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>316</start>
<end>326</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T 利用图像描述与知识图谱增强表示的视觉问答(Exploiting Image Captions and External Knowledge as Representation Enhancement for Visual Question Answering)
%A Wang, Gechao
%A Zhu, Muhua
%A Xu, Chen
%A Zhang, Yan
%A Wang, Huizhen
%A Zhu, Jingbo
%Y Li, Sheng
%Y Sun, Maosong
%Y Liu, Yang
%Y Wu, Hua
%Y Liu, Kang
%Y Che, Wanxiang
%Y He, Shizhu
%Y Rao, Gaoqi
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 August
%I Chinese Information Processing Society of China
%C Huhhot, China
%G Chinese
%F wang-etal-2021-li
%X 视觉问答作为多模态任务,需要深度理解图像和文本问题从而推理出答案。然而在许多情况下,仅在图像和问题上进行简单推理难以得到正确的答案,事实上还有其它有效的信息可以被利用,例如图像描述、外部知识等。针对以上问题,本文提出了利用图像描述和外部知识增强表示的视觉问答模型。该模型以问题为导向,基于协同注意力机制分别在图像和其描述上进行编码,并且利用知识图谱嵌入,将外部知识编码到模型当中,丰富了模型的特征表示,增强模型的推理能力。在OKVQA数据集上的实验结果表明本文方法相比基线系统有1.71%的准确率提升,与先前工作中的主流模型相比也有1.88%的准确率提升,证明了本文方法的有效性。
%U https://aclanthology.org/2021.ccl-1.30
%P 316-326
Markdown (Informal)
[利用图像描述与知识图谱增强表示的视觉问答(Exploiting Image Captions and External Knowledge as Representation Enhancement for Visual Question Answering)](https://aclanthology.org/2021.ccl-1.30) (Wang et al., CCL 2021)
ACL