@inproceedings{hakimov-etal-2022-tib,
title = "{TIB}-{VA} at {S}em{E}val-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memes",
author = "Hakimov, Sherzod and
Cheema, Gullal Singh and
Ewerth, Ralph",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.105/",
doi = "10.18653/v1/2022.semeval-1.105",
pages = "756--760",
abstract = "The detection of offensive, hateful content on social media is a challenging problem that affects many online users on a daily basis. Hateful content is often used to target a group of people based on ethnicity, gender, religion and other factors. The hate or contempt toward women has been increasing on social platforms. Misogynous content detection is especially challenging when textual and visual modalities are combined to form a single context, e.g., an overlay text embedded on top of an image, also known as \textit{meme}. In this paper, we present a multimodal architecture that combines textual and visual features to detect misogynous memes. The proposed architecture is evaluated in the SemEval-2022 Task 5: MAMI - Multimedia Automatic Misogyny Identification challenge under the team name TIB-VA. We obtained the best result in the Task-B where the challenge is to classify whether a given document is misogynous and further identify the following sub-classes: shaming, stereotype, objectification, and violence."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hakimov-etal-2022-tib">
<titleInfo>
<title>TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sherzod</namePart>
<namePart type="family">Hakimov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gullal</namePart>
<namePart type="given">Singh</namePart>
<namePart type="family">Cheema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ralph</namePart>
<namePart type="family">Ewerth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</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">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The detection of offensive, hateful content on social media is a challenging problem that affects many online users on a daily basis. Hateful content is often used to target a group of people based on ethnicity, gender, religion and other factors. The hate or contempt toward women has been increasing on social platforms. Misogynous content detection is especially challenging when textual and visual modalities are combined to form a single context, e.g., an overlay text embedded on top of an image, also known as meme. In this paper, we present a multimodal architecture that combines textual and visual features to detect misogynous memes. The proposed architecture is evaluated in the SemEval-2022 Task 5: MAMI - Multimedia Automatic Misogyny Identification challenge under the team name TIB-VA. We obtained the best result in the Task-B where the challenge is to classify whether a given document is misogynous and further identify the following sub-classes: shaming, stereotype, objectification, and violence.</abstract>
<identifier type="citekey">hakimov-etal-2022-tib</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.105</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.105/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>756</start>
<end>760</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memes
%A Hakimov, Sherzod
%A Cheema, Gullal Singh
%A Ewerth, Ralph
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F hakimov-etal-2022-tib
%X The detection of offensive, hateful content on social media is a challenging problem that affects many online users on a daily basis. Hateful content is often used to target a group of people based on ethnicity, gender, religion and other factors. The hate or contempt toward women has been increasing on social platforms. Misogynous content detection is especially challenging when textual and visual modalities are combined to form a single context, e.g., an overlay text embedded on top of an image, also known as meme. In this paper, we present a multimodal architecture that combines textual and visual features to detect misogynous memes. The proposed architecture is evaluated in the SemEval-2022 Task 5: MAMI - Multimedia Automatic Misogyny Identification challenge under the team name TIB-VA. We obtained the best result in the Task-B where the challenge is to classify whether a given document is misogynous and further identify the following sub-classes: shaming, stereotype, objectification, and violence.
%R 10.18653/v1/2022.semeval-1.105
%U https://aclanthology.org/2022.semeval-1.105/
%U https://doi.org/10.18653/v1/2022.semeval-1.105
%P 756-760
Markdown (Informal)
[TIB-VA at SemEval-2022 Task 5: A Multimodal Architecture for the Detection and Classification of Misogynous Memes](https://aclanthology.org/2022.semeval-1.105/) (Hakimov et al., SemEval 2022)
ACL