@inproceedings{zeng-2021-multi,
title = "Multi Task Learning based Framework for Multimodal Classification",
author = "Zeng, Danting",
editor = "Zadeh, Amir and
Morency, Louis-Philippe and
Liang, Paul Pu and
Ross, Candace and
Salakhutdinov, Ruslan and
Poria, Soujanya and
Cambria, Erik and
Shi, Kelly",
booktitle = "Proceedings of the Third Workshop on Multimodal Artificial Intelligence",
month = jun,
year = "2021",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.maiworkshop-1.5",
doi = "10.18653/v1/2021.maiworkshop-1.5",
pages = "30--35",
abstract = "Large-scale multi-modal classification aim to distinguish between different multi-modal data, and it has drawn dramatically attentions since last decade. In this paper, we propose a multi-task learning-based framework for the multimodal classification task, which consists of two branches: multi-modal autoencoder branch and attention-based multi-modal modeling branch. Multi-modal autoencoder can receive multi-modal features and obtain the interactive information which called multi-modal encoder feature, and use this feature to reconstitute all the input data. Besides, multi-modal encoder feature can be used to enrich the raw dataset, and improve the performance of downstream tasks (such as classification task). As for attention-based multimodal modeling branch, we first employ attention mechanism to make the model focused on important features, then we use the multi-modal encoder feature to enrich the input information, achieve a better performance. We conduct extensive experiments on different dataset, the results demonstrate the effectiveness of proposed framework.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-2021-multi">
<titleInfo>
<title>Multi Task Learning based Framework for Multimodal Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Danting</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Multimodal Artificial Intelligence</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Zadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Louis-Philippe</namePart>
<namePart type="family">Morency</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="given">Pu</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Candace</namePart>
<namePart type="family">Ross</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Salakhutdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Cambria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kelly</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale multi-modal classification aim to distinguish between different multi-modal data, and it has drawn dramatically attentions since last decade. In this paper, we propose a multi-task learning-based framework for the multimodal classification task, which consists of two branches: multi-modal autoencoder branch and attention-based multi-modal modeling branch. Multi-modal autoencoder can receive multi-modal features and obtain the interactive information which called multi-modal encoder feature, and use this feature to reconstitute all the input data. Besides, multi-modal encoder feature can be used to enrich the raw dataset, and improve the performance of downstream tasks (such as classification task). As for attention-based multimodal modeling branch, we first employ attention mechanism to make the model focused on important features, then we use the multi-modal encoder feature to enrich the input information, achieve a better performance. We conduct extensive experiments on different dataset, the results demonstrate the effectiveness of proposed framework.</abstract>
<identifier type="citekey">zeng-2021-multi</identifier>
<identifier type="doi">10.18653/v1/2021.maiworkshop-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.maiworkshop-1.5</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>30</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi Task Learning based Framework for Multimodal Classification
%A Zeng, Danting
%Y Zadeh, Amir
%Y Morency, Louis-Philippe
%Y Liang, Paul Pu
%Y Ross, Candace
%Y Salakhutdinov, Ruslan
%Y Poria, Soujanya
%Y Cambria, Erik
%Y Shi, Kelly
%S Proceedings of the Third Workshop on Multimodal Artificial Intelligence
%D 2021
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F zeng-2021-multi
%X Large-scale multi-modal classification aim to distinguish between different multi-modal data, and it has drawn dramatically attentions since last decade. In this paper, we propose a multi-task learning-based framework for the multimodal classification task, which consists of two branches: multi-modal autoencoder branch and attention-based multi-modal modeling branch. Multi-modal autoencoder can receive multi-modal features and obtain the interactive information which called multi-modal encoder feature, and use this feature to reconstitute all the input data. Besides, multi-modal encoder feature can be used to enrich the raw dataset, and improve the performance of downstream tasks (such as classification task). As for attention-based multimodal modeling branch, we first employ attention mechanism to make the model focused on important features, then we use the multi-modal encoder feature to enrich the input information, achieve a better performance. We conduct extensive experiments on different dataset, the results demonstrate the effectiveness of proposed framework.
%R 10.18653/v1/2021.maiworkshop-1.5
%U https://aclanthology.org/2021.maiworkshop-1.5
%U https://doi.org/10.18653/v1/2021.maiworkshop-1.5
%P 30-35
Markdown (Informal)
[Multi Task Learning based Framework for Multimodal Classification](https://aclanthology.org/2021.maiworkshop-1.5) (Zeng, maiworkshop 2021)
ACL