<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-long-2023-improving">
    <titleInfo>
        <title>Improving Cross-modal Alignment for Text-Guided Image Inpainting</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yucheng</namePart>
        <namePart type="family">Zhou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guodong</namePart>
        <namePart type="family">Long</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Andreas</namePart>
            <namePart type="family">Vlachos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Isabelle</namePart>
            <namePart type="family">Augenstein</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dubrovnik, Croatia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Text-guided image inpainting (TGII) aims to restore missing regions based on a given text in a damaged image. Existing methods are based on a strong vision encoder and a cross-modal fusion model to integrate cross-modal features. However, these methods allocate most of the computation to visual encoding, while light computation on modeling modality interactions. Moreover, they take cross-modal fusion for depth features, which ignores a fine-grained alignment between text and image. Recently, vision-language pre-trained models (VLPM), encapsulating rich cross-modal alignment knowledge, have advanced in most multimodal tasks. In this work, we propose a novel model for TGII by improving cross-modal alignment (CMA). CMA model consists of a VLPM as a vision-language encoder, an image generator and global-local discriminators. To explore cross-modal alignment knowledge for image restoration, we introduce cross-modal alignment distillation and in-sample distribution distillation. In addition, we employ adversarial training to enhance the model to fill the missing region in complicated structures effectively. Experiments are conducted on two popular vision-language datasets. Results show that our model achieves state-of-the-art performance compared with other strong competitors.</abstract>
    <identifier type="citekey">zhou-long-2023-improving</identifier>
    <identifier type="doi">10.18653/v1/2023.eacl-main.250</identifier>
    <location>
        <url>https://aclanthology.org/2023.eacl-main.250</url>
    </location>
    <part>
        <date>2023-05</date>
        <extent unit="page">
            <start>3445</start>
            <end>3456</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Cross-modal Alignment for Text-Guided Image Inpainting
%A Zhou, Yucheng
%A Long, Guodong
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F zhou-long-2023-improving
%X Text-guided image inpainting (TGII) aims to restore missing regions based on a given text in a damaged image. Existing methods are based on a strong vision encoder and a cross-modal fusion model to integrate cross-modal features. However, these methods allocate most of the computation to visual encoding, while light computation on modeling modality interactions. Moreover, they take cross-modal fusion for depth features, which ignores a fine-grained alignment between text and image. Recently, vision-language pre-trained models (VLPM), encapsulating rich cross-modal alignment knowledge, have advanced in most multimodal tasks. In this work, we propose a novel model for TGII by improving cross-modal alignment (CMA). CMA model consists of a VLPM as a vision-language encoder, an image generator and global-local discriminators. To explore cross-modal alignment knowledge for image restoration, we introduce cross-modal alignment distillation and in-sample distribution distillation. In addition, we employ adversarial training to enhance the model to fill the missing region in complicated structures effectively. Experiments are conducted on two popular vision-language datasets. Results show that our model achieves state-of-the-art performance compared with other strong competitors.
%R 10.18653/v1/2023.eacl-main.250
%U https://aclanthology.org/2023.eacl-main.250
%U https://doi.org/10.18653/v1/2023.eacl-main.250
%P 3445-3456

Markdown (Informal)

[Improving Cross-modal Alignment for Text-Guided Image Inpainting](https://aclanthology.org/2023.eacl-main.250) (Zhou & Long, EACL 2023)

• Improving Cross-modal Alignment for Text-Guided Image Inpainting (Zhou & Long, EACL 2023)

ACL

• Yucheng Zhou and Guodong Long. 2023. Improving Cross-modal Alignment for Text-Guided Image Inpainting. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 3445–3456, Dubrovnik, Croatia. Association for Computational Linguistics.