<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="waheed-an-2025-image">
    <titleInfo>
        <title>Image Embedding Sampling Method for Diverse Captioning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sania</namePart>
        <namePart type="family">Waheed</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Na</namePart>
        <namePart type="given">Min</namePart>
        <namePart type="family">An</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices and assistive technologies. Alternatively, comparably smaller VLMs prioritize high-level scene descriptions, overlooking finer details that contribute to a richer understanding of an image. In this paper, we introduce a training-free framework that enhances caption diversity and informativeness by explicitly attending to distinct image regions using a comparably small VLM, BLIP, as the backbone. Our approach leverages structured segmentation to produce hierarchical representations that capture both global and localized semantics. Without requiring additional model training, we demonstrate that our method allows smaller VLMs to achieve performance comparable to larger models in terms of image-caption alignment, semantic integrity, and diversity. We evaluate our framework on MSCOCO, Flickr30k, and Nocaps test datasets, achieving a Div-2 score of 0.735, 0.750, and 0.748 for each dataset, respectively, while maintaining strong image-caption relevancy and semantic integrity with the human-annotated captions. Our code is available at https://github.com/xfactlab/HBoP.</abstract>
    <identifier type="citekey">waheed-an-2025-image</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.156/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>3141</start>
            <end>3157</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Image Embedding Sampling Method for Diverse Captioning
%A Waheed, Sania
%A An, Na Min
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F waheed-an-2025-image
%X Image Captioning for state-of-the-art VLMs has significantly improved over time; however, this comes at the cost of increased computational complexity, making them less accessible for resource-constrained applications such as mobile devices and assistive technologies. Alternatively, comparably smaller VLMs prioritize high-level scene descriptions, overlooking finer details that contribute to a richer understanding of an image. In this paper, we introduce a training-free framework that enhances caption diversity and informativeness by explicitly attending to distinct image regions using a comparably small VLM, BLIP, as the backbone. Our approach leverages structured segmentation to produce hierarchical representations that capture both global and localized semantics. Without requiring additional model training, we demonstrate that our method allows smaller VLMs to achieve performance comparable to larger models in terms of image-caption alignment, semantic integrity, and diversity. We evaluate our framework on MSCOCO, Flickr30k, and Nocaps test datasets, achieving a Div-2 score of 0.735, 0.750, and 0.748 for each dataset, respectively, while maintaining strong image-caption relevancy and semantic integrity with the human-annotated captions. Our code is available at https://github.com/xfactlab/HBoP.
%U https://aclanthology.org/2025.emnlp-main.156/
%P 3141-3157

Markdown (Informal)

[Image Embedding Sampling Method for Diverse Captioning](https://aclanthology.org/2025.emnlp-main.156/) (Waheed & An, EMNLP 2025)

• Image Embedding Sampling Method for Diverse Captioning (Waheed & An, EMNLP 2025)

ACL

• Sania Waheed and Na Min An. 2025. Image Embedding Sampling Method for Diverse Captioning. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 3141–3157, Suzhou, China. Association for Computational Linguistics.