@inproceedings{huang-etal-2020-aligned,
title = "Aligned Dual Channel Graph Convolutional Network for Visual Question Answering",
author = "Huang, Qingbao and
Wei, Jielong and
Cai, Yi and
Zheng, Changmeng and
Chen, Junying and
Leung, Ho-fung and
Li, Qing",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.642",
doi = "10.18653/v1/2020.acl-main.642",
pages = "7166--7176",
abstract = "Visual question answering aims to answer the natural language question about a given image. Existing graph-based methods only focus on the relations between objects in an image and neglect the importance of the syntactic dependency relations between words in a question. To simultaneously capture the relations between objects in an image and the syntactic dependency relations between words in a question, we propose a novel dual channel graph convolutional network (DC-GCN) for better combining visual and textual advantages. The DC-GCN model consists of three parts: an I-GCN module to capture the relations between objects in an image, a Q-GCN module to capture the syntactic dependency relations between words in a question, and an attention alignment module to align image representations and question representations. Experimental results show that our model achieves comparable performance with the state-of-the-art approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2020-aligned">
<titleInfo>
<title>Aligned Dual Channel Graph Convolutional Network for Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qingbao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jielong</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changmeng</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junying</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ho-fung</namePart>
<namePart type="family">Leung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qing</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Visual question answering aims to answer the natural language question about a given image. Existing graph-based methods only focus on the relations between objects in an image and neglect the importance of the syntactic dependency relations between words in a question. To simultaneously capture the relations between objects in an image and the syntactic dependency relations between words in a question, we propose a novel dual channel graph convolutional network (DC-GCN) for better combining visual and textual advantages. The DC-GCN model consists of three parts: an I-GCN module to capture the relations between objects in an image, a Q-GCN module to capture the syntactic dependency relations between words in a question, and an attention alignment module to align image representations and question representations. Experimental results show that our model achieves comparable performance with the state-of-the-art approaches.</abstract>
<identifier type="citekey">huang-etal-2020-aligned</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.642</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.642</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>7166</start>
<end>7176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligned Dual Channel Graph Convolutional Network for Visual Question Answering
%A Huang, Qingbao
%A Wei, Jielong
%A Cai, Yi
%A Zheng, Changmeng
%A Chen, Junying
%A Leung, Ho-fung
%A Li, Qing
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F huang-etal-2020-aligned
%X Visual question answering aims to answer the natural language question about a given image. Existing graph-based methods only focus on the relations between objects in an image and neglect the importance of the syntactic dependency relations between words in a question. To simultaneously capture the relations between objects in an image and the syntactic dependency relations between words in a question, we propose a novel dual channel graph convolutional network (DC-GCN) for better combining visual and textual advantages. The DC-GCN model consists of three parts: an I-GCN module to capture the relations between objects in an image, a Q-GCN module to capture the syntactic dependency relations between words in a question, and an attention alignment module to align image representations and question representations. Experimental results show that our model achieves comparable performance with the state-of-the-art approaches.
%R 10.18653/v1/2020.acl-main.642
%U https://aclanthology.org/2020.acl-main.642
%U https://doi.org/10.18653/v1/2020.acl-main.642
%P 7166-7176
Markdown (Informal)
[Aligned Dual Channel Graph Convolutional Network for Visual Question Answering](https://aclanthology.org/2020.acl-main.642) (Huang et al., ACL 2020)
ACL