@inproceedings{arora-etal-2024-text-multimodal,
title = "Text-to-Multimodal Retrieval with Bimodal Input Fusion in Shared Cross-Modal Transformer",
author = "Arora, Pranav and
Pehlivan, Selen and
Laaksonen, Jorma",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1374",
pages = "15823--15834",
abstract = "The rapid proliferation of multimedia content has necessitated the development of effective multimodal video retrieval systems. Multimodal video retrieval is a non-trivial task involving retrieval of relevant information across different modalities, such as text, audio, and visual. This work aims to improve multimodal retrieval by guiding the creation of a shared embedding space with task-specific contrastive loss functions. An important aspect of our work is to propose a model that learns retrieval cues for the textual query from multiple modalities both separately and jointly within a hierarchical architecture that can be flexibly extended and fine-tuned for any number of modalities. To this end, the loss functions and the architectural design of the model are developed with a strong focus on increasing the mutual information between the textual and cross-modal representations. The proposed approach is quantitatively evaluated on the MSR-VTT and YouCook2 text-to-video retrieval benchmark datasets. The results showcase that the approach not only holds its own against state-of-the-art methods, but also outperforms them in a number of scenarios, with a notable relative improvements from baseline in R@1, R@5 and R@10 metrics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="arora-etal-2024-text-multimodal">
<titleInfo>
<title>Text-to-Multimodal Retrieval with Bimodal Input Fusion in Shared Cross-Modal Transformer</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Arora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Selen</namePart>
<namePart type="family">Pehlivan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorma</namePart>
<namePart type="family">Laaksonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The rapid proliferation of multimedia content has necessitated the development of effective multimodal video retrieval systems. Multimodal video retrieval is a non-trivial task involving retrieval of relevant information across different modalities, such as text, audio, and visual. This work aims to improve multimodal retrieval by guiding the creation of a shared embedding space with task-specific contrastive loss functions. An important aspect of our work is to propose a model that learns retrieval cues for the textual query from multiple modalities both separately and jointly within a hierarchical architecture that can be flexibly extended and fine-tuned for any number of modalities. To this end, the loss functions and the architectural design of the model are developed with a strong focus on increasing the mutual information between the textual and cross-modal representations. The proposed approach is quantitatively evaluated on the MSR-VTT and YouCook2 text-to-video retrieval benchmark datasets. The results showcase that the approach not only holds its own against state-of-the-art methods, but also outperforms them in a number of scenarios, with a notable relative improvements from baseline in R@1, R@5 and R@10 metrics.</abstract>
<identifier type="citekey">arora-etal-2024-text-multimodal</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1374</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15823</start>
<end>15834</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text-to-Multimodal Retrieval with Bimodal Input Fusion in Shared Cross-Modal Transformer
%A Arora, Pranav
%A Pehlivan, Selen
%A Laaksonen, Jorma
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F arora-etal-2024-text-multimodal
%X The rapid proliferation of multimedia content has necessitated the development of effective multimodal video retrieval systems. Multimodal video retrieval is a non-trivial task involving retrieval of relevant information across different modalities, such as text, audio, and visual. This work aims to improve multimodal retrieval by guiding the creation of a shared embedding space with task-specific contrastive loss functions. An important aspect of our work is to propose a model that learns retrieval cues for the textual query from multiple modalities both separately and jointly within a hierarchical architecture that can be flexibly extended and fine-tuned for any number of modalities. To this end, the loss functions and the architectural design of the model are developed with a strong focus on increasing the mutual information between the textual and cross-modal representations. The proposed approach is quantitatively evaluated on the MSR-VTT and YouCook2 text-to-video retrieval benchmark datasets. The results showcase that the approach not only holds its own against state-of-the-art methods, but also outperforms them in a number of scenarios, with a notable relative improvements from baseline in R@1, R@5 and R@10 metrics.
%U https://aclanthology.org/2024.lrec-main.1374
%P 15823-15834
Markdown (Informal)
[Text-to-Multimodal Retrieval with Bimodal Input Fusion in Shared Cross-Modal Transformer](https://aclanthology.org/2024.lrec-main.1374) (Arora et al., LREC-COLING 2024)
ACL