@inproceedings{mallik-etal-2025-cuet,
title = "{CUET}-823@{D}ravidian{L}ang{T}ech 2025: Shared Task on Multimodal Misogyny Meme Detection in {T}amil Language",
author = "Mallik, Arpita and
Dhar, Ratnajit and
Das, Udoy and
Labib, Momtazul Arefin and
Rahman, Samia and
Murad, Hasan",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Sherly, Elizabeth and
Rajiakodi, Saranya and
Palani, Balasubramanian and
Subramanian, Malliga and
Cn, Subalalitha and
Chinnappa, Dhivya",
booktitle = "Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages",
month = may,
year = "2025",
address = "Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.dravidianlangtech-1.57/",
doi = "10.18653/v1/2025.dravidianlangtech-1.57",
pages = "325--329",
ISBN = "979-8-89176-228-2",
abstract = "Misogynous content on social media, especially in memes, present challenges due to the complex reciprocation of text and images that carry offensive messages. This difficulty mostly arises from the lack of direct alignment between modalities and biases in large-scale visio-linguistic models. In this paper, we present our system for the Shared Task on Misogyny Meme Detection - DravidianLangTech@NAACL 2025. We have implemented various unimodal models, such as mBERT and IndicBERT for text data, and ViT, ResNet, and EfficientNet for image data. Moreover, we have tried combining these models and finally adopted a multimodal approach that combined mBERT for text and EfficientNet for image features, both fine-tuned to better interpret subtle language and detailed visuals. The fused features are processed through a dense neural network for classification. Our approach achieved an F1 score of 0.78120, securing 4th place and demonstrating the potential of transformer-based architectures and state-of-the-art CNNs for this task."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mallik-etal-2025-cuet">
<titleInfo>
<title>CUET-823@DravidianLangTech 2025: Shared Task on Multimodal Misogyny Meme Detection in Tamil Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arpita</namePart>
<namePart type="family">Mallik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ratnajit</namePart>
<namePart type="family">Dhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udoy</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Momtazul</namePart>
<namePart type="given">Arefin</namePart>
<namePart type="family">Labib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Murad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Madasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sajeetha</namePart>
<namePart type="family">Thavareesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malliga</namePart>
<namePart type="family">Subramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhivya</namePart>
<namePart type="family">Chinnappa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-228-2</identifier>
</relatedItem>
<abstract>Misogynous content on social media, especially in memes, present challenges due to the complex reciprocation of text and images that carry offensive messages. This difficulty mostly arises from the lack of direct alignment between modalities and biases in large-scale visio-linguistic models. In this paper, we present our system for the Shared Task on Misogyny Meme Detection - DravidianLangTech@NAACL 2025. We have implemented various unimodal models, such as mBERT and IndicBERT for text data, and ViT, ResNet, and EfficientNet for image data. Moreover, we have tried combining these models and finally adopted a multimodal approach that combined mBERT for text and EfficientNet for image features, both fine-tuned to better interpret subtle language and detailed visuals. The fused features are processed through a dense neural network for classification. Our approach achieved an F1 score of 0.78120, securing 4th place and demonstrating the potential of transformer-based architectures and state-of-the-art CNNs for this task.</abstract>
<identifier type="citekey">mallik-etal-2025-cuet</identifier>
<identifier type="doi">10.18653/v1/2025.dravidianlangtech-1.57</identifier>
<location>
<url>https://aclanthology.org/2025.dravidianlangtech-1.57/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>325</start>
<end>329</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET-823@DravidianLangTech 2025: Shared Task on Multimodal Misogyny Meme Detection in Tamil Language
%A Mallik, Arpita
%A Dhar, Ratnajit
%A Das, Udoy
%A Labib, Momtazul Arefin
%A Rahman, Samia
%A Murad, Hasan
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Sherly, Elizabeth
%Y Rajiakodi, Saranya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Cn, Subalalitha
%Y Chinnappa, Dhivya
%S Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2025
%8 May
%I Association for Computational Linguistics
%C Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico
%@ 979-8-89176-228-2
%F mallik-etal-2025-cuet
%X Misogynous content on social media, especially in memes, present challenges due to the complex reciprocation of text and images that carry offensive messages. This difficulty mostly arises from the lack of direct alignment between modalities and biases in large-scale visio-linguistic models. In this paper, we present our system for the Shared Task on Misogyny Meme Detection - DravidianLangTech@NAACL 2025. We have implemented various unimodal models, such as mBERT and IndicBERT for text data, and ViT, ResNet, and EfficientNet for image data. Moreover, we have tried combining these models and finally adopted a multimodal approach that combined mBERT for text and EfficientNet for image features, both fine-tuned to better interpret subtle language and detailed visuals. The fused features are processed through a dense neural network for classification. Our approach achieved an F1 score of 0.78120, securing 4th place and demonstrating the potential of transformer-based architectures and state-of-the-art CNNs for this task.
%R 10.18653/v1/2025.dravidianlangtech-1.57
%U https://aclanthology.org/2025.dravidianlangtech-1.57/
%U https://doi.org/10.18653/v1/2025.dravidianlangtech-1.57
%P 325-329
Markdown (Informal)
[CUET-823@DravidianLangTech 2025: Shared Task on Multimodal Misogyny Meme Detection in Tamil Language](https://aclanthology.org/2025.dravidianlangtech-1.57/) (Mallik et al., DravidianLangTech 2025)
ACL
- Arpita Mallik, Ratnajit Dhar, Udoy Das, Momtazul Arefin Labib, Samia Rahman, and Hasan Murad. 2025. CUET-823@DravidianLangTech 2025: Shared Task on Multimodal Misogyny Meme Detection in Tamil Language. In Proceedings of the Fifth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages, pages 325–329, Acoma, The Albuquerque Convention Center, Albuquerque, New Mexico. Association for Computational Linguistics.