<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2026-videoevent">
    <titleInfo>
        <title>VideoEvent: Leveraging Relevance and LLMs for Video Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chen-Chen</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ming-Han</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">KunRu</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yu-Chee</namePart>
        <namePart type="family">Tseng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Núria</namePart>
            <namePart type="family">Bel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Henk</namePart>
            <namePart type="family">van den Heuvel</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nancy</namePart>
            <namePart type="family">Ide</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Simon</namePart>
            <namePart type="family">Krek</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Antonio</namePart>
            <namePart type="family">Toral</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>ELRA Language Resource Association</publisher>
            <place>
                <placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We propose VideoEvent, a lightweight and efficient training-free framework for Video Question Answering (VQA) with large language models (LLMs). Although several training-free VQA methods have been proposed, they often neglect the temporal dependencies between frames or clips, treating them as isolated units and relying on complex or resource-intensive components. To address this limitation while maintaining performance and simplicity, we propose VideoEvent, a framework that segments an input video into question-relevant temporal events and selectively supplements them with low-level visual cues such as background and object layout. Our method selects semantically relevant time spans and retrieves one representative background frame to enrich the prompt to LLM. This design minimizes reliance on additional tools and reduces inference cost, making it highly suitable for practical deployment. Experimental results on EgoSchema and NExT-QA show that VideoEvent reduces inference cost by up to 30% while maintaining state-of-the-art accuracy, and its background module improves accuracy by 1–3% across multiple frameworks.</abstract>
    <identifier type="citekey">lin-etal-2026-videoevent</identifier>
    <identifier type="doi">10.63317/5dnrdsjog6tj</identifier>
    <location>
        <url>https://aclanthology.org/2026.lrec-1.395/</url>
    </location>
    <part>
        <date>2026-05</date>
        <extent unit="page">
            <start>5024</start>
            <end>5034</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T VideoEvent: Leveraging Relevance and LLMs for Video Question Answering
%A Lin, Chen-Chen
%A Lee, Ming-Han
%A Wu, KunRu
%A Tseng, Yu-Chee
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F lin-etal-2026-videoevent
%X We propose VideoEvent, a lightweight and efficient training-free framework for Video Question Answering (VQA) with large language models (LLMs). Although several training-free VQA methods have been proposed, they often neglect the temporal dependencies between frames or clips, treating them as isolated units and relying on complex or resource-intensive components. To address this limitation while maintaining performance and simplicity, we propose VideoEvent, a framework that segments an input video into question-relevant temporal events and selectively supplements them with low-level visual cues such as background and object layout. Our method selects semantically relevant time spans and retrieves one representative background frame to enrich the prompt to LLM. This design minimizes reliance on additional tools and reduces inference cost, making it highly suitable for practical deployment. Experimental results on EgoSchema and NExT-QA show that VideoEvent reduces inference cost by up to 30% while maintaining state-of-the-art accuracy, and its background module improves accuracy by 1–3% across multiple frameworks.
%R 10.63317/5dnrdsjog6tj
%U https://aclanthology.org/2026.lrec-1.395/
%U https://doi.org/10.63317/5dnrdsjog6tj
%P 5024-5034

Markdown (Informal)

[VideoEvent: Leveraging Relevance and LLMs for Video Question Answering](https://aclanthology.org/2026.lrec-1.395/) (Lin et al., LREC 2026)

• VideoEvent: Leveraging Relevance and LLMs for Video Question Answering (Lin et al., LREC 2026)

ACL

• Chen-Chen Lin, Ming-Han Lee, KunRu Wu, and Yu-Chee Tseng. 2026. VideoEvent: Leveraging Relevance and LLMs for Video Question Answering. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 5024–5034, Palma de Mallorca, Spain. ELRA Language Resource Association.