@inproceedings{tian-etal-2024-learning,
title = "Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition",
author = "Tian, Yuanhe and
Xia, Fei and
Song, Yan",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.391",
pages = "6561--6573",
abstract = "In many practical scenarios, contents from different modalities are not semantically aligned; for instance, visual and textual information may conflict with each other, resulting in non-compositional expression effects such as irony or humor. Effective modeling and smooth integration of multimodal information are crucial for achieving good understanding of the contrast across modalities. Being focusing on image-text matching, most current studies face challenges in identifying such contrast, leading to limitations in exploring the extended semantics when images and texts do not match. In this paper, we propose an LLM-based approach for learning multimodal contrast following the encoding-decoding paradigm, enhanced by a memory module with reinforced contrast recognition, and use a series of tasks that have the nature of multimodal contrast to verify our approach. The memory module learns the integration between visual and textual features with trainable memory vectors and the reinforced contrast recognition uses self-rejection sampling to optimize the memory to further enhance learning multimodal contrast. The resulted information, accompanied with visual and text features, is finally fed into the LLM to predict corresponding labels. We experiment our approach on four English and Chinese benchmark datasets, where it outperforms strong baselines and state-of-the-art studies.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-etal-2024-learning">
<titleInfo>
<title>Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuanhe</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In many practical scenarios, contents from different modalities are not semantically aligned; for instance, visual and textual information may conflict with each other, resulting in non-compositional expression effects such as irony or humor. Effective modeling and smooth integration of multimodal information are crucial for achieving good understanding of the contrast across modalities. Being focusing on image-text matching, most current studies face challenges in identifying such contrast, leading to limitations in exploring the extended semantics when images and texts do not match. In this paper, we propose an LLM-based approach for learning multimodal contrast following the encoding-decoding paradigm, enhanced by a memory module with reinforced contrast recognition, and use a series of tasks that have the nature of multimodal contrast to verify our approach. The memory module learns the integration between visual and textual features with trainable memory vectors and the reinforced contrast recognition uses self-rejection sampling to optimize the memory to further enhance learning multimodal contrast. The resulted information, accompanied with visual and text features, is finally fed into the LLM to predict corresponding labels. We experiment our approach on four English and Chinese benchmark datasets, where it outperforms strong baselines and state-of-the-art studies.</abstract>
<identifier type="citekey">tian-etal-2024-learning</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.391</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>6561</start>
<end>6573</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition
%A Tian, Yuanhe
%A Xia, Fei
%A Song, Yan
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F tian-etal-2024-learning
%X In many practical scenarios, contents from different modalities are not semantically aligned; for instance, visual and textual information may conflict with each other, resulting in non-compositional expression effects such as irony or humor. Effective modeling and smooth integration of multimodal information are crucial for achieving good understanding of the contrast across modalities. Being focusing on image-text matching, most current studies face challenges in identifying such contrast, leading to limitations in exploring the extended semantics when images and texts do not match. In this paper, we propose an LLM-based approach for learning multimodal contrast following the encoding-decoding paradigm, enhanced by a memory module with reinforced contrast recognition, and use a series of tasks that have the nature of multimodal contrast to verify our approach. The memory module learns the integration between visual and textual features with trainable memory vectors and the reinforced contrast recognition uses self-rejection sampling to optimize the memory to further enhance learning multimodal contrast. The resulted information, accompanied with visual and text features, is finally fed into the LLM to predict corresponding labels. We experiment our approach on four English and Chinese benchmark datasets, where it outperforms strong baselines and state-of-the-art studies.
%U https://aclanthology.org/2024.findings-acl.391
%P 6561-6573
Markdown (Informal)
[Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition](https://aclanthology.org/2024.findings-acl.391) (Tian et al., Findings 2024)
ACL