<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-satoh-2023-referring">
    <titleInfo>
        <title>Referring Image Segmentation via Joint Mask Contextual Embedding Learning and Progressive Alignment Network</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ziling</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shin’ichi</namePart>
        <namePart type="family">Satoh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Referring image segmentation is a task that aims to predict pixel-wise masks corresponding to objects in an image described by natural language expressions. Previous methods for referring image segmentation employ a cascade framework to break down complex problems into multiple stages. However, its defects also obvious: existing methods within the cascade framework may encounter challenges in both maintaining a strong focus on the most relevant information during specific stages of the referring image segmentation process and rectifying errors propagated from early stages, which can ultimately result in sub-optimal performance. To address these limitations, we propose the Joint Mask Contextual Embedding Learning Network (JMCELN). JMCELN is designed to enhance the Cascade Framework by incorporating a Learnable Contextual Embedding and a Progressive Alignment Network (PAN). The Learnable Contextual Embedding module dynamically stores and utilizes reasoning information based on the current mask prediction results, enabling the network to adaptively capture and refine pertinent information for improved mask prediction accuracy. Furthermore, the Progressive Alignment Network (PAN) is introduced as an integral part of JMCELN. PAN leverages the output from the previous layer as a filter for the current output, effectively reducing inconsistencies between predictions from different stages. By iteratively aligning the predictions, PAN guides the Learnable Contextual Embedding to incorporate more discriminative information for reasoning, leading to enhanced prediction quality and a reduction in error propagation. With these methods, we achieved state-of-the-art results on three commonly used benchmarks, especially in more intricate datasets. The code will be released.</abstract>
    <identifier type="citekey">huang-satoh-2023-referring</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.481</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.481</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>7753</start>
            <end>7762</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Referring Image Segmentation via Joint Mask Contextual Embedding Learning and Progressive Alignment Network
%A Huang, Ziling
%A Satoh, Shin’ichi
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F huang-satoh-2023-referring
%X Referring image segmentation is a task that aims to predict pixel-wise masks corresponding to objects in an image described by natural language expressions. Previous methods for referring image segmentation employ a cascade framework to break down complex problems into multiple stages. However, its defects also obvious: existing methods within the cascade framework may encounter challenges in both maintaining a strong focus on the most relevant information during specific stages of the referring image segmentation process and rectifying errors propagated from early stages, which can ultimately result in sub-optimal performance. To address these limitations, we propose the Joint Mask Contextual Embedding Learning Network (JMCELN). JMCELN is designed to enhance the Cascade Framework by incorporating a Learnable Contextual Embedding and a Progressive Alignment Network (PAN). The Learnable Contextual Embedding module dynamically stores and utilizes reasoning information based on the current mask prediction results, enabling the network to adaptively capture and refine pertinent information for improved mask prediction accuracy. Furthermore, the Progressive Alignment Network (PAN) is introduced as an integral part of JMCELN. PAN leverages the output from the previous layer as a filter for the current output, effectively reducing inconsistencies between predictions from different stages. By iteratively aligning the predictions, PAN guides the Learnable Contextual Embedding to incorporate more discriminative information for reasoning, leading to enhanced prediction quality and a reduction in error propagation. With these methods, we achieved state-of-the-art results on three commonly used benchmarks, especially in more intricate datasets. The code will be released.
%R 10.18653/v1/2023.emnlp-main.481
%U https://aclanthology.org/2023.emnlp-main.481
%U https://doi.org/10.18653/v1/2023.emnlp-main.481
%P 7753-7762

Markdown (Informal)

[Referring Image Segmentation via Joint Mask Contextual Embedding Learning and Progressive Alignment Network](https://aclanthology.org/2023.emnlp-main.481) (Huang & Satoh, EMNLP 2023)

• Referring Image Segmentation via Joint Mask Contextual Embedding Learning and Progressive Alignment Network (Huang & Satoh, EMNLP 2023)

ACL

• Ziling Huang and Shin’ichi Satoh. 2023. Referring Image Segmentation via Joint Mask Contextual Embedding Learning and Progressive Alignment Network. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7753–7762, Singapore. Association for Computational Linguistics.