@inproceedings{i-dutta-2026-projukti,
title = "Projukti {K}avalan@{MML}ow 2026: Weighted Visual Frame and Cross-modal Fusion for Misogynistic Video Detection in {D}ravidian Language",
author = "I, Palaniraj and
Dutta, Dwaipayan",
editor = "Ponnusamy, Rahul and
Kumaresan, Prasanna Kumar and
Rajiakodi, Saranya and
B, Premjith and
MC, Shunmuga Priya and
Murugappan, Abirami and
G, Jyothish Lal and
V, Sowmya and
Chakravarthi, Bharathi Raja",
booktitle = "Proceedings of the Fifth Workshop on Multimodal Machine Learning in Low-resource Languages",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mmlow-main.8/",
pages = "76--85",
ISBN = "979-8-89176-445-3",
abstract = "Misogyny and hate content have become a serious issue in the current digital era. Such content predominantly manifests as short video clips, making automated detection mechanisms imperative for social media platforms. To effectively classify such videos, a multimodal setup is required, as video data contains image frames, audio clips, and text captions. The multimodal misogyny video classification task aims to combine all audio, visual, and extracted text information. Conventional methods typically aim to process this extracted information in parallel to reach a conclusion. Our proposed framework utilizes the pre-trained models DINOv2, wav2vec 2.0, and MuRiL-large to embed visual, audio, and text features, respectively. To mitigate overfitting on datasets of different sizes, we propose a dual-architecture approach: we utilize a regularized Gated Early-Fusion Network (EF-Net) for the highly constrained Tamil dataset, and a deeper Cross-Modal Temporal Attention Network (TA-Net) with an ensemble strategy for the Malayalam dataset. Ultimately, our framework achieved a 68.8{\%} macro-F1 score for the Malayalam dataset and an 80.7{\%} macro-F1 score for the Tamil dataset, securing Rank 1 in misogyny video classification for both languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="i-dutta-2026-projukti">
<titleInfo>
<title>Projukti Kavalan@MMLow 2026: Weighted Visual Frame and Cross-modal Fusion for Misogynistic Video Detection in Dravidian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Palaniraj</namePart>
<namePart type="family">I</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dwaipayan</namePart>
<namePart type="family">Dutta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on Multimodal Machine Learning in Low-resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Ponnusamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasanna</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Kumaresan</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">Premjith</namePart>
<namePart type="family">B</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shunmuga</namePart>
<namePart type="given">Priya</namePart>
<namePart type="family">MC</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abirami</namePart>
<namePart type="family">Murugappan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jyothish</namePart>
<namePart type="given">Lal</namePart>
<namePart type="family">G</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sowmya</namePart>
<namePart type="family">V</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-445-3</identifier>
</relatedItem>
<abstract>Misogyny and hate content have become a serious issue in the current digital era. Such content predominantly manifests as short video clips, making automated detection mechanisms imperative for social media platforms. To effectively classify such videos, a multimodal setup is required, as video data contains image frames, audio clips, and text captions. The multimodal misogyny video classification task aims to combine all audio, visual, and extracted text information. Conventional methods typically aim to process this extracted information in parallel to reach a conclusion. Our proposed framework utilizes the pre-trained models DINOv2, wav2vec 2.0, and MuRiL-large to embed visual, audio, and text features, respectively. To mitigate overfitting on datasets of different sizes, we propose a dual-architecture approach: we utilize a regularized Gated Early-Fusion Network (EF-Net) for the highly constrained Tamil dataset, and a deeper Cross-Modal Temporal Attention Network (TA-Net) with an ensemble strategy for the Malayalam dataset. Ultimately, our framework achieved a 68.8% macro-F1 score for the Malayalam dataset and an 80.7% macro-F1 score for the Tamil dataset, securing Rank 1 in misogyny video classification for both languages.</abstract>
<identifier type="citekey">i-dutta-2026-projukti</identifier>
<location>
<url>https://aclanthology.org/2026.mmlow-main.8/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>76</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Projukti Kavalan@MMLow 2026: Weighted Visual Frame and Cross-modal Fusion for Misogynistic Video Detection in Dravidian Language
%A I, Palaniraj
%A Dutta, Dwaipayan
%Y Ponnusamy, Rahul
%Y Kumaresan, Prasanna Kumar
%Y Rajiakodi, Saranya
%Y B, Premjith
%Y MC, Shunmuga Priya
%Y Murugappan, Abirami
%Y G, Jyothish Lal
%Y V, Sowmya
%Y Chakravarthi, Bharathi Raja
%S Proceedings of the Fifth Workshop on Multimodal Machine Learning in Low-resource Languages
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-445-3
%F i-dutta-2026-projukti
%X Misogyny and hate content have become a serious issue in the current digital era. Such content predominantly manifests as short video clips, making automated detection mechanisms imperative for social media platforms. To effectively classify such videos, a multimodal setup is required, as video data contains image frames, audio clips, and text captions. The multimodal misogyny video classification task aims to combine all audio, visual, and extracted text information. Conventional methods typically aim to process this extracted information in parallel to reach a conclusion. Our proposed framework utilizes the pre-trained models DINOv2, wav2vec 2.0, and MuRiL-large to embed visual, audio, and text features, respectively. To mitigate overfitting on datasets of different sizes, we propose a dual-architecture approach: we utilize a regularized Gated Early-Fusion Network (EF-Net) for the highly constrained Tamil dataset, and a deeper Cross-Modal Temporal Attention Network (TA-Net) with an ensemble strategy for the Malayalam dataset. Ultimately, our framework achieved a 68.8% macro-F1 score for the Malayalam dataset and an 80.7% macro-F1 score for the Tamil dataset, securing Rank 1 in misogyny video classification for both languages.
%U https://aclanthology.org/2026.mmlow-main.8/
%P 76-85
Markdown (Informal)
[Projukti Kavalan@MMLow 2026: Weighted Visual Frame and Cross-modal Fusion for Misogynistic Video Detection in Dravidian Language](https://aclanthology.org/2026.mmlow-main.8/) (I & Dutta, MMLow 2026)
ACL