@inproceedings{iyer-etal-2026-team,
title = "{T}eam{\_}{O}ne@{D}ravidian{L}ang{T}ech 2026: A Gated Multimodal Architecture for Multi-Level Stance and Target Detection in {M}alayalam Political Memes",
author = "Iyer, Nimisha M and
N, Ashmi S and
Palani, Balasubramanian and
Jose, Jobin and
Rajamanickam, Siranjeevi",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Thavareesan, Sajeetha and
Rajiakodi, Saranya and
Navaneethakrishnan, Subalalitha and
Chinnappa, Dhivya and
Palani, Balasubramanian and
Subramanian, Malliga and
Shanmugavadivel, Kogilavani and
Rajalakshmi, Ratnavel",
booktitle = "Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for {D}ravidian Languages",
month = jul,
year = "2026",
address = "Underline (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.dravidianlangtech-1.65/",
pages = "409--413",
ISBN = "979-8-89176-401-9",
abstract = "Stance and target detection in multimodal political memes presents notable challenges in low-resource and highly imbalanced settings.This task is based on the Malayalam dataset from the DravidianLangTech 2026 Shared Task(500 samples with a 95.4:4.6 stance imbalance).The primary challenges stem from linguistic variability and visually complex meme formats,which hinder accurate text extraction and effective multimodal alignment. A lightweight yet high-performing multimodal framework is proposed that integrates bilingual OCR, a Vision Transformer (ViT), and IndicBERT to learn complementary visual and textual representations. A gated fusion mechanism effectivelycombines multimodal features, while asymmetric loss weighting and post-training threshold optimization address extreme class imbalance. The methodology achieves a Weighted F1-score of 0.9535 for stance detection and 0.5283 for target identification, demonstrating strong robustness and generalization under realistic multimodal constraints."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="iyer-etal-2026-team">
<titleInfo>
<title>Team_One@DravidianLangTech 2026: A Gated Multimodal Architecture for Multi-Level Stance and Target Detection in Malayalam Political Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nimisha</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Iyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashmi</namePart>
<namePart type="given">S</namePart>
<namePart type="family">N</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Balasubramanian</namePart>
<namePart type="family">Palani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jobin</namePart>
<namePart type="family">Jose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siranjeevi</namePart>
<namePart type="family">Rajamanickam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth 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">Saranya</namePart>
<namePart type="family">Rajiakodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Subalalitha</namePart>
<namePart type="family">Navaneethakrishnan</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>
<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">Kogilavani</namePart>
<namePart type="family">Shanmugavadivel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ratnavel</namePart>
<namePart type="family">Rajalakshmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Underline (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-401-9</identifier>
</relatedItem>
<abstract>Stance and target detection in multimodal political memes presents notable challenges in low-resource and highly imbalanced settings.This task is based on the Malayalam dataset from the DravidianLangTech 2026 Shared Task(500 samples with a 95.4:4.6 stance imbalance).The primary challenges stem from linguistic variability and visually complex meme formats,which hinder accurate text extraction and effective multimodal alignment. A lightweight yet high-performing multimodal framework is proposed that integrates bilingual OCR, a Vision Transformer (ViT), and IndicBERT to learn complementary visual and textual representations. A gated fusion mechanism effectivelycombines multimodal features, while asymmetric loss weighting and post-training threshold optimization address extreme class imbalance. The methodology achieves a Weighted F1-score of 0.9535 for stance detection and 0.5283 for target identification, demonstrating strong robustness and generalization under realistic multimodal constraints.</abstract>
<identifier type="citekey">iyer-etal-2026-team</identifier>
<location>
<url>https://aclanthology.org/2026.dravidianlangtech-1.65/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>409</start>
<end>413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Team_One@DravidianLangTech 2026: A Gated Multimodal Architecture for Multi-Level Stance and Target Detection in Malayalam Political Memes
%A Iyer, Nimisha M.
%A N, Ashmi S.
%A Palani, Balasubramanian
%A Jose, Jobin
%A Rajamanickam, Siranjeevi
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Thavareesan, Sajeetha
%Y Rajiakodi, Saranya
%Y Navaneethakrishnan, Subalalitha
%Y Chinnappa, Dhivya
%Y Palani, Balasubramanian
%Y Subramanian, Malliga
%Y Shanmugavadivel, Kogilavani
%Y Rajalakshmi, Ratnavel
%S Proceedings of the Sixth Workshop on Speech, Vision, and Language Technologies for Dravidian Languages
%D 2026
%8 July
%I Association for Computational Linguistics
%C Underline (Virtual)
%@ 979-8-89176-401-9
%F iyer-etal-2026-team
%X Stance and target detection in multimodal political memes presents notable challenges in low-resource and highly imbalanced settings.This task is based on the Malayalam dataset from the DravidianLangTech 2026 Shared Task(500 samples with a 95.4:4.6 stance imbalance).The primary challenges stem from linguistic variability and visually complex meme formats,which hinder accurate text extraction and effective multimodal alignment. A lightweight yet high-performing multimodal framework is proposed that integrates bilingual OCR, a Vision Transformer (ViT), and IndicBERT to learn complementary visual and textual representations. A gated fusion mechanism effectivelycombines multimodal features, while asymmetric loss weighting and post-training threshold optimization address extreme class imbalance. The methodology achieves a Weighted F1-score of 0.9535 for stance detection and 0.5283 for target identification, demonstrating strong robustness and generalization under realistic multimodal constraints.
%U https://aclanthology.org/2026.dravidianlangtech-1.65/
%P 409-413
Markdown (Informal)
[Team_One@DravidianLangTech 2026: A Gated Multimodal Architecture for Multi-Level Stance and Target Detection in Malayalam Political Memes](https://aclanthology.org/2026.dravidianlangtech-1.65/) (Iyer et al., DravidianLangTech 2026)
ACL