<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bilen-etal-2026-visaffect">
    <titleInfo>
        <title>VisAffect at MWE-2026 AdMIRe 2: IMMCAN Idiom Multimodal Cross-Attention Network</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Barış</namePart>
        <namePart type="family">Bilen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ali</namePart>
        <namePart type="family">Azmoudeh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hazım</namePart>
        <namePart type="given">Kemal</namePart>
        <namePart type="family">Ekenel</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hatice</namePart>
        <namePart type="family">Kose</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Atul</namePart>
            <namePart type="given">Kr.</namePart>
            <namePart type="family">Ojha</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Verginica</namePart>
            <namePart type="given">Barbu</namePart>
            <namePart type="family">Mititelu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mathieu</namePart>
            <namePart type="family">Constant</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ivelina</namePart>
            <namePart type="family">Stoyanova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">A</namePart>
            <namePart type="given">Seza</namePart>
            <namePart type="family">Doğruöz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alexandre</namePart>
            <namePart type="family">Rademaker</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Rabat, Marocco</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-363-0</identifier>
    </relatedItem>
    <abstract>We address AdMIRe 2.0, a static image ranking task where a sentence containing a potentially idiomatic expression is paired with five image–caption candidates, and the goal is to rank the candidates by semantic compatibility with the intended idiomatic or literal meaning. We propose IMMCAN, which keeps XLM-R and Jina-CLIP-v2 frozen and learns a lightweight two-stage cross-attention fusion, caption–image grounding followed by idiom-to-multimodal conditioning, to predict a compatibility score per candidate. We also evaluate caption-only augmentation via back-translation and synonym substitution, and compare regression and rank-class formulations. On AdMIRe 1.0, text-only achieves higher test top-image accuracy than VLM-grounded modeling. In contrast, on AdMIRe 2.0 zero-shot, adding visual patch grounding improves both accuracy and NDCG indicating better cross-lingual ranking transfer.</abstract>
    <identifier type="citekey">bilen-etal-2026-visaffect</identifier>
    <location>
        <url>https://aclanthology.org/2026.mwe-1.19/</url>
    </location>
    <part>
        <date>2026-03</date>
        <extent unit="page">
            <start>149</start>
            <end>153</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T VisAffect at MWE-2026 AdMIRe 2: IMMCAN Idiom Multimodal Cross-Attention Network
%A Bilen, Barış
%A Azmoudeh, Ali
%A Ekenel, Hazım Kemal
%A Kose, Hatice
%Y Ojha, Atul Kr.
%Y Mititelu, Verginica Barbu
%Y Constant, Mathieu
%Y Stoyanova, Ivelina
%Y Doğruöz, A. Seza
%Y Rademaker, Alexandre
%S Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Marocco
%@ 979-8-89176-363-0
%F bilen-etal-2026-visaffect
%X We address AdMIRe 2.0, a static image ranking task where a sentence containing a potentially idiomatic expression is paired with five image–caption candidates, and the goal is to rank the candidates by semantic compatibility with the intended idiomatic or literal meaning. We propose IMMCAN, which keeps XLM-R and Jina-CLIP-v2 frozen and learns a lightweight two-stage cross-attention fusion, caption–image grounding followed by idiom-to-multimodal conditioning, to predict a compatibility score per candidate. We also evaluate caption-only augmentation via back-translation and synonym substitution, and compare regression and rank-class formulations. On AdMIRe 1.0, text-only achieves higher test top-image accuracy than VLM-grounded modeling. In contrast, on AdMIRe 2.0 zero-shot, adding visual patch grounding improves both accuracy and NDCG indicating better cross-lingual ranking transfer.
%U https://aclanthology.org/2026.mwe-1.19/
%P 149-153

Markdown (Informal)

[VisAffect at MWE-2026 AdMIRe 2: IMMCAN Idiom Multimodal Cross-Attention Network](https://aclanthology.org/2026.mwe-1.19/) (Bilen et al., MWE 2026)

• VisAffect at MWE-2026 AdMIRe 2: IMMCAN Idiom Multimodal Cross-Attention Network (Bilen et al., MWE 2026)

ACL

• Barış Bilen, Ali Azmoudeh, Hazım Kemal Ekenel, and Hatice Kose. 2026. VisAffect at MWE-2026 AdMIRe 2: IMMCAN Idiom Multimodal Cross-Attention Network. In Proceedings of the 22nd Workshop on Multiword Expressions (MWE 2026), pages 149–153, Rabat, Marocco. Association for Computational Linguistics.