<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kralev-2025-fusion">
    <titleInfo>
        <title>Fusion of Object-Centric and Linguistic Features for Domain-Adapted Multimodal Learning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jordan</namePart>
        <namePart type="given">Konstantinov</namePart>
        <namePart type="family">Kralev</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Kunilovskaya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie</namePart>
            <namePart type="family">Escribe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Modern multimodal systems often struggle to link domain-specific visual content with textual descriptions, especially when object recognition is limited to general categories (e.g. COCO classes) and lacks customised adaptation to language models. In this paper, we present a novel framework that integrates a domain-specific adapted Detectron2 model into predefined models via a trainable projection layer, enabling precise crossmodal adaptation for specialised domains. Our approach extends Detectron2’s recognition capabilities to new categories by fine-tuning on multi-domain datasets, while a lightweight linear projection layer maps region-based visual features to the model’s embedding space without completely retraining the model. We evaluated the framework for domain-specific image captioning. The presented approach provides a scalable design for combining domain-specific visual recognition with language inference, with applications in domains that require fine-grained multimodal understanding.</abstract>
    <identifier type="citekey">kralev-2025-fusion</identifier>
    <location>
        <url>https://aclanthology.org/2025.ranlp-1.69/</url>
    </location>
    <part>
        <date>2025-09</date>
        <extent unit="page">
            <start>587</start>
            <end>594</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Fusion of Object-Centric and Linguistic Features for Domain-Adapted Multimodal Learning
%A Kralev, Jordan Konstantinov
%Y Angelova, Galia
%Y Kunilovskaya, Maria
%Y Escribe, Marie
%Y Mitkov, Ruslan
%S Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F kralev-2025-fusion
%X Modern multimodal systems often struggle to link domain-specific visual content with textual descriptions, especially when object recognition is limited to general categories (e.g. COCO classes) and lacks customised adaptation to language models. In this paper, we present a novel framework that integrates a domain-specific adapted Detectron2 model into predefined models via a trainable projection layer, enabling precise crossmodal adaptation for specialised domains. Our approach extends Detectron2’s recognition capabilities to new categories by fine-tuning on multi-domain datasets, while a lightweight linear projection layer maps region-based visual features to the model’s embedding space without completely retraining the model. We evaluated the framework for domain-specific image captioning. The presented approach provides a scalable design for combining domain-specific visual recognition with language inference, with applications in domains that require fine-grained multimodal understanding.
%U https://aclanthology.org/2025.ranlp-1.69/
%P 587-594

Markdown (Informal)

[Fusion of Object-Centric and Linguistic Features for Domain-Adapted Multimodal Learning](https://aclanthology.org/2025.ranlp-1.69/) (Kralev, RANLP 2025)

• Fusion of Object-Centric and Linguistic Features for Domain-Adapted Multimodal Learning (Kralev, RANLP 2025)

ACL

• Jordan Konstantinov Kralev. 2025. Fusion of Object-Centric and Linguistic Features for Domain-Adapted Multimodal Learning. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing - Natural Language Processing in the Generative AI Era, pages 587–594, Varna, Bulgaria. INCOMA Ltd., Shoumen, Bulgaria.