@inproceedings{wang-etal-2021-mirtt-learning,
title = "{MIRTT}: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering",
author = "Wang, Junjie and
Ji, Yatai and
Sun, Jiaqi and
Yang, Yujiu and
Sakai, Tetsuya",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.196",
doi = "10.18653/v1/2021.findings-emnlp.196",
pages = "2280--2292",
abstract = "In Visual Question Answering (VQA), existing bilinear methods focus on the interaction between images and questions. As a result, the answers are either spliced into the questions or utilized as labels only for classification. On the other hand, trilinear models such as the CTI model efficiently utilize the inter-modality information between answers, questions, and images, while ignoring intra-modality information. Inspired by this observation, we propose a new trilinear interaction framework called MIRTT (Learning Multimodal Interaction Representations from Trilinear Transformers), incorporating the attention mechanisms for capturing inter-modality and intra-modality relationships. Moreover, we design a two-stage workflow where a bilinear model reduces the free-form, open-ended VQA problem into a multiple-choice VQA problem. Furthermore, to obtain accurate and generic multimodal representations, we pre-train MIRTT with masked language prediction. Our method achieves state-of-the-art performance on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperforms bilinear baselines on the VQA-2.0, TDIUC and GQA datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-mirtt-learning">
<titleInfo>
<title>MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junjie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yatai</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujiu</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tetsuya</namePart>
<namePart type="family">Sakai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In Visual Question Answering (VQA), existing bilinear methods focus on the interaction between images and questions. As a result, the answers are either spliced into the questions or utilized as labels only for classification. On the other hand, trilinear models such as the CTI model efficiently utilize the inter-modality information between answers, questions, and images, while ignoring intra-modality information. Inspired by this observation, we propose a new trilinear interaction framework called MIRTT (Learning Multimodal Interaction Representations from Trilinear Transformers), incorporating the attention mechanisms for capturing inter-modality and intra-modality relationships. Moreover, we design a two-stage workflow where a bilinear model reduces the free-form, open-ended VQA problem into a multiple-choice VQA problem. Furthermore, to obtain accurate and generic multimodal representations, we pre-train MIRTT with masked language prediction. Our method achieves state-of-the-art performance on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperforms bilinear baselines on the VQA-2.0, TDIUC and GQA datasets.</abstract>
<identifier type="citekey">wang-etal-2021-mirtt-learning</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.196</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.196</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2280</start>
<end>2292</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering
%A Wang, Junjie
%A Ji, Yatai
%A Sun, Jiaqi
%A Yang, Yujiu
%A Sakai, Tetsuya
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F wang-etal-2021-mirtt-learning
%X In Visual Question Answering (VQA), existing bilinear methods focus on the interaction between images and questions. As a result, the answers are either spliced into the questions or utilized as labels only for classification. On the other hand, trilinear models such as the CTI model efficiently utilize the inter-modality information between answers, questions, and images, while ignoring intra-modality information. Inspired by this observation, we propose a new trilinear interaction framework called MIRTT (Learning Multimodal Interaction Representations from Trilinear Transformers), incorporating the attention mechanisms for capturing inter-modality and intra-modality relationships. Moreover, we design a two-stage workflow where a bilinear model reduces the free-form, open-ended VQA problem into a multiple-choice VQA problem. Furthermore, to obtain accurate and generic multimodal representations, we pre-train MIRTT with masked language prediction. Our method achieves state-of-the-art performance on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperforms bilinear baselines on the VQA-2.0, TDIUC and GQA datasets.
%R 10.18653/v1/2021.findings-emnlp.196
%U https://aclanthology.org/2021.findings-emnlp.196
%U https://doi.org/10.18653/v1/2021.findings-emnlp.196
%P 2280-2292
Markdown (Informal)
[MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering](https://aclanthology.org/2021.findings-emnlp.196) (Wang et al., Findings 2021)
ACL