<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diao-etal-2025-learning">
    <titleInfo>
        <title>Learning Sparsity for Effective and Efficient Music Performance Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xingjian</namePart>
        <namePart type="family">Diao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tianzhen</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chunhui</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weiyi</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ming</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiang</namePart>
        <namePart type="family">Gui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-252-7</identifier>
    </relatedItem>
    <abstract>Music performances, characterized by dense and continuous audio as well as seamless audio-visual integration, present unique challenges for multimodal scene understanding and reasoning. Recent Music Performance Audio-Visual Question Answering (Music AVQA) datasets have been proposed to reflect these challenges, highlighting the continued need for more effective integration of audio-visual representations in complex question answering. However, existing Music AVQA methods often rely on dense and unoptimized representations, leading to inefficiencies in the isolation of key information, the reduction of redundancy, and the prioritization of critical samples. To address these challenges, we introduce Sparsify, a sparse learning framework specifically designed for Music AVQA. It integrates three sparsification strategies into an end-to-end pipeline and achieves state-of-the-art performance on the Music AVQA datasets. In addition, it reduces training time by 28.32% compared to its fully trained dense counterpart while maintaining accuracy, demonstrating clear efficiency gains. To further improve data efficiency, we propose a key-subset selection algorithm that selects and uses approximately 25% of MUSIC-AVQA v2.0 training data and retains 70–80% of full-data performance across models.</abstract>
    <identifier type="citekey">diao-etal-2025-learning</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-short.12</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-short.12/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>136</start>
            <end>146</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning Sparsity for Effective and Efficient Music Performance Question Answering
%A Diao, Xingjian
%A Yang, Tianzhen
%A Zhang, Chunhui
%A Wu, Weiyi
%A Cheng, Ming
%A Gui, Jiang
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-252-7
%F diao-etal-2025-learning
%X Music performances, characterized by dense and continuous audio as well as seamless audio-visual integration, present unique challenges for multimodal scene understanding and reasoning. Recent Music Performance Audio-Visual Question Answering (Music AVQA) datasets have been proposed to reflect these challenges, highlighting the continued need for more effective integration of audio-visual representations in complex question answering. However, existing Music AVQA methods often rely on dense and unoptimized representations, leading to inefficiencies in the isolation of key information, the reduction of redundancy, and the prioritization of critical samples. To address these challenges, we introduce Sparsify, a sparse learning framework specifically designed for Music AVQA. It integrates three sparsification strategies into an end-to-end pipeline and achieves state-of-the-art performance on the Music AVQA datasets. In addition, it reduces training time by 28.32% compared to its fully trained dense counterpart while maintaining accuracy, demonstrating clear efficiency gains. To further improve data efficiency, we propose a key-subset selection algorithm that selects and uses approximately 25% of MUSIC-AVQA v2.0 training data and retains 70–80% of full-data performance across models.
%R 10.18653/v1/2025.acl-short.12
%U https://aclanthology.org/2025.acl-short.12/
%U https://doi.org/10.18653/v1/2025.acl-short.12
%P 136-146

Markdown (Informal)

[Learning Sparsity for Effective and Efficient Music Performance Question Answering](https://aclanthology.org/2025.acl-short.12/) (Diao et al., ACL 2025)

• Learning Sparsity for Effective and Efficient Music Performance Question Answering (Diao et al., ACL 2025)

ACL

• Xingjian Diao, Tianzhen Yang, Chunhui Zhang, Weiyi Wu, Ming Cheng, and Jiang Gui. 2025. Learning Sparsity for Effective and Efficient Music Performance Question Answering. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 136–146, Vienna, Austria. Association for Computational Linguistics.