<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guan-etal-2025-cot">
    <titleInfo>
        <title>CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xikang</namePart>
        <namePart type="family">Guan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zheng</namePart>
        <namePart type="family">Gu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jing</namePart>
        <namePart type="family">Huo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tianyu</namePart>
        <namePart type="family">Ding</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Gao</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>The application of visual-to-music generation (VTM) is rapidly growing. However, current VTM methods struggle with capturing the relationship between visuals and music in open-domain settings, mainly due to two challenges: the lack of large-scale, high-quality visual-music paired datasets and the absence of direct semantic correspondence between visuals and music. In this work, we propose CoT-VTM, a framework that distills Chain-of-Thought (CoT) reasoning to enable visual-to-music generation without paired data, while efficiently producing music aligned with visual content in open-domain settings. We first bridge the gap between visual, music, and text data using appropriate foundation models. Next, we identify key elements of the visual-music relationship and design a CoT prompt for visual-to-music mapping. To fully distill the reasoning of CoT, we incorporate latent information from intermediate reasoning steps as supervisory signals alongside visual and music supervision. Finally, we design a two-stage mapping distillation training process: the first stage uses discriminative MLP modules, while the second uses a generative embedding diffusion model (EDM). Our model achieves optimal performance on both image-to-music and video-to-music tasks. Project page: https://xxkkxxx.github.io/cot-vtm/</abstract>
    <identifier type="citekey">guan-etal-2025-cot</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.647</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.647/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>12493</start>
            <end>12510</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning
%A Guan, Xikang
%A Gu, Zheng
%A Huo, Jing
%A Ding, Tianyu
%A Gao, Yang
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F guan-etal-2025-cot
%X The application of visual-to-music generation (VTM) is rapidly growing. However, current VTM methods struggle with capturing the relationship between visuals and music in open-domain settings, mainly due to two challenges: the lack of large-scale, high-quality visual-music paired datasets and the absence of direct semantic correspondence between visuals and music. In this work, we propose CoT-VTM, a framework that distills Chain-of-Thought (CoT) reasoning to enable visual-to-music generation without paired data, while efficiently producing music aligned with visual content in open-domain settings. We first bridge the gap between visual, music, and text data using appropriate foundation models. Next, we identify key elements of the visual-music relationship and design a CoT prompt for visual-to-music mapping. To fully distill the reasoning of CoT, we incorporate latent information from intermediate reasoning steps as supervisory signals alongside visual and music supervision. Finally, we design a two-stage mapping distillation training process: the first stage uses discriminative MLP modules, while the second uses a generative embedding diffusion model (EDM). Our model achieves optimal performance on both image-to-music and video-to-music tasks. Project page: https://xxkkxxx.github.io/cot-vtm/
%R 10.18653/v1/2025.findings-acl.647
%U https://aclanthology.org/2025.findings-acl.647/
%U https://doi.org/10.18653/v1/2025.findings-acl.647
%P 12493-12510

Markdown (Informal)

[CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning](https://aclanthology.org/2025.findings-acl.647/) (Guan et al., Findings 2025)

• CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning (Guan et al., Findings 2025)

ACL

• Xikang Guan, Zheng Gu, Jing Huo, Tianyu Ding, and Yang Gao. 2025. CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning. In Findings of the Association for Computational Linguistics: ACL 2025, pages 12493–12510, Vienna, Austria. Association for Computational Linguistics.