<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saha-gokhale-2026-zero">
    <titleInfo>
        <title>Zero-Shot Multimodal Retrieval with Multi-Scale Contextual Representations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sourajit</namePart>
        <namePart type="family">Saha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tejas</namePart>
        <namePart type="family">Gokhale</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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-390-6</identifier>
    </relatedItem>
    <abstract>In multimodal information retrieval (MMIR), candidates relevant to an input query need to be retrieved from a database, where the query and database items span different modalities. As real-world databases evolve, repeatedly annotating and indexing data and re-optimizing domain-specific models across modalities is impractical. We present MULTI-SCORE, a fine-tuning-free, two-stage MMIR approach that couples efficient candidate filtering with fine-grained multimodal re-ranking. Stage-1 adopts Matryoshka representations to efficiently filter out low-relevance candidates without expensive similarity computations on full-scale representations for the entire database. Stage-2 re-ranks the filtered candidates by computing their fine-grained multimodal contextual representations with two scoring functions for semantic alignment using chain-of-thought prompting and question-answering. Experiments demonstrate state-of-the-art zero-shot retrieval on 12 MMIR tasks across 32 datasets while outperforming supervised methods on 23 datasets.</abstract>
    <identifier type="citekey">saha-gokhale-2026-zero</identifier>
    <identifier type="doi">10.18653/v1/2026.acl-long.930</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-long.930/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>20304</start>
            <end>20324</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Zero-Shot Multimodal Retrieval with Multi-Scale Contextual Representations
%A Saha, Sourajit
%A Gokhale, Tejas
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F saha-gokhale-2026-zero
%X In multimodal information retrieval (MMIR), candidates relevant to an input query need to be retrieved from a database, where the query and database items span different modalities. As real-world databases evolve, repeatedly annotating and indexing data and re-optimizing domain-specific models across modalities is impractical. We present MULTI-SCORE, a fine-tuning-free, two-stage MMIR approach that couples efficient candidate filtering with fine-grained multimodal re-ranking. Stage-1 adopts Matryoshka representations to efficiently filter out low-relevance candidates without expensive similarity computations on full-scale representations for the entire database. Stage-2 re-ranks the filtered candidates by computing their fine-grained multimodal contextual representations with two scoring functions for semantic alignment using chain-of-thought prompting and question-answering. Experiments demonstrate state-of-the-art zero-shot retrieval on 12 MMIR tasks across 32 datasets while outperforming supervised methods on 23 datasets.
%R 10.18653/v1/2026.acl-long.930
%U https://aclanthology.org/2026.acl-long.930/
%U https://doi.org/10.18653/v1/2026.acl-long.930
%P 20304-20324

Markdown (Informal)

[Zero-Shot Multimodal Retrieval with Multi-Scale Contextual Representations](https://aclanthology.org/2026.acl-long.930/) (Saha & Gokhale, ACL 2026)

• Zero-Shot Multimodal Retrieval with Multi-Scale Contextual Representations (Saha & Gokhale, ACL 2026)

ACL

• Sourajit Saha and Tejas Gokhale. 2026. Zero-Shot Multimodal Retrieval with Multi-Scale Contextual Representations. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 20304–20324, San Diego, California, United States. Association for Computational Linguistics.