<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-read">
    <titleInfo>
        <title>Read Before Grounding: Scene Knowledge Visual Grounding via Multi-step Parsing</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">HaiXiang</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lixian</namePart>
        <namePart type="family">Su</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">ShuangMing</namePart>
        <namePart type="family">Mao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jing</namePart>
        <namePart type="family">Ye</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-01</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 31st International Conference on Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Owen</namePart>
            <namePart type="family">Rambow</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Leo</namePart>
            <namePart type="family">Wanner</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marianna</namePart>
            <namePart type="family">Apidianaki</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Hend</namePart>
            <namePart type="family">Al-Khalifa</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Barbara</namePart>
            <namePart type="given">Di</namePart>
            <namePart type="family">Eugenio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Steven</namePart>
            <namePart type="family">Schockaert</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Abu Dhabi, UAE</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Visual grounding (VG) is an important task in vision and language that involves understanding the mutual relationship between query terms and images. However, existing VG datasets typically use simple and intuitive textual descriptions, with limited attribute and spatial information between images and text. Recently, the Scene Knowledge Visual Grounding (SK-VG) task has been introduced, which constructs VG datasets using visual knowledge and relational referential expressions. Due to the length of textual visual knowledge and the complexity of the referential relationships between entities, previous models have struggled with this task. Therefore, we propose ReadVG, a zero-shot, plug-and-play method that leverages the robust language understanding capabilities of Large Language Models (LLMs) to transform long visual knowledge texts into concise, information-dense visual descriptions. To improve the accuracy of target localisation, we employ a multi-step parsing algorithm that can progressively extract the query targets and their features from the visual knowledge and relational referencing expressions, thereby assisting multimodal models to more accurately localise the target for grounding purposes. Extensive experiments and case studies show that our approach can significantly improve the performance of multimodal grounding models.</abstract>
    <identifier type="citekey">zhu-etal-2025-read</identifier>
    <location>
        <url>https://aclanthology.org/2025.coling-main.76/</url>
    </location>
    <part>
        <date>2025-01</date>
        <extent unit="page">
            <start>1136</start>
            <end>1149</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Read Before Grounding: Scene Knowledge Visual Grounding via Multi-step Parsing
%A Zhu, HaiXiang
%A Su, Lixian
%A Mao, ShuangMing
%A Ye, Jing
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F zhu-etal-2025-read
%X Visual grounding (VG) is an important task in vision and language that involves understanding the mutual relationship between query terms and images. However, existing VG datasets typically use simple and intuitive textual descriptions, with limited attribute and spatial information between images and text. Recently, the Scene Knowledge Visual Grounding (SK-VG) task has been introduced, which constructs VG datasets using visual knowledge and relational referential expressions. Due to the length of textual visual knowledge and the complexity of the referential relationships between entities, previous models have struggled with this task. Therefore, we propose ReadVG, a zero-shot, plug-and-play method that leverages the robust language understanding capabilities of Large Language Models (LLMs) to transform long visual knowledge texts into concise, information-dense visual descriptions. To improve the accuracy of target localisation, we employ a multi-step parsing algorithm that can progressively extract the query targets and their features from the visual knowledge and relational referencing expressions, thereby assisting multimodal models to more accurately localise the target for grounding purposes. Extensive experiments and case studies show that our approach can significantly improve the performance of multimodal grounding models.
%U https://aclanthology.org/2025.coling-main.76/
%P 1136-1149

Markdown (Informal)

[Read Before Grounding: Scene Knowledge Visual Grounding via Multi-step Parsing](https://aclanthology.org/2025.coling-main.76/) (Zhu et al., COLING 2025)

• Read Before Grounding: Scene Knowledge Visual Grounding via Multi-step Parsing (Zhu et al., COLING 2025)

ACL

• HaiXiang Zhu, Lixian Su, ShuangMing Mao, and Jing Ye. 2025. Read Before Grounding: Scene Knowledge Visual Grounding via Multi-step Parsing. In Proceedings of the 31st International Conference on Computational Linguistics, pages 1136–1149, Abu Dhabi, UAE. Association for Computational Linguistics.