@inproceedings{xiao-etal-2024-vanessa,
title = "Vanessa: Visual Connotation and Aesthetic Attributes Understanding Network for Multimodal Aspect-based Sentiment Analysis",
author = "Xiao, Luwei and
Mao, Rui and
Zhang, Xulang and
He, Liang and
Cambria, Erik",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.671/",
doi = "10.18653/v1/2024.findings-emnlp.671",
pages = "11486--11500",
abstract = "Prevailing research concentrates on superficial features or descriptions of images, revealing a significant gap in the systematic exploration of their connotative and aesthetic attributes. Furthermore, the use of cross-modal relation detection modules to eliminate noise from comprehensive image representations leads to the omission of subtle contextual information. In this paper, we present a Visual Connotation and Aesthetic Attributes Understanding Network (Vanessa) for Multimodal Aspect-based Sentiment Analysis. Concretely, Vanessa incorporates a Multi-Aesthetic Attributes Aggregation (MA3) module that models intra- and inter-dependencies among bi-modal representations as well as emotion-laden aesthetic attributes. Moreover, we devise a self-supervised contrastive learning framework to explore the pairwise relevance between images and text via the Gaussian distribution of their CLIP scores. By dynamically clustering and merging multi-modal tokens, Vanessa effectively captures both implicit and explicit sentimental cues. Extensive experiments on widely adopted two benchmarks verify Vanessa`s effectiveness."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2024-vanessa">
<titleInfo>
<title>Vanessa: Visual Connotation and Aesthetic Attributes Understanding Network for Multimodal Aspect-based Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luwei</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xulang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Cambria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prevailing research concentrates on superficial features or descriptions of images, revealing a significant gap in the systematic exploration of their connotative and aesthetic attributes. Furthermore, the use of cross-modal relation detection modules to eliminate noise from comprehensive image representations leads to the omission of subtle contextual information. In this paper, we present a Visual Connotation and Aesthetic Attributes Understanding Network (Vanessa) for Multimodal Aspect-based Sentiment Analysis. Concretely, Vanessa incorporates a Multi-Aesthetic Attributes Aggregation (MA3) module that models intra- and inter-dependencies among bi-modal representations as well as emotion-laden aesthetic attributes. Moreover, we devise a self-supervised contrastive learning framework to explore the pairwise relevance between images and text via the Gaussian distribution of their CLIP scores. By dynamically clustering and merging multi-modal tokens, Vanessa effectively captures both implicit and explicit sentimental cues. Extensive experiments on widely adopted two benchmarks verify Vanessa‘s effectiveness.</abstract>
<identifier type="citekey">xiao-etal-2024-vanessa</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.671</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.671/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>11486</start>
<end>11500</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Vanessa: Visual Connotation and Aesthetic Attributes Understanding Network for Multimodal Aspect-based Sentiment Analysis
%A Xiao, Luwei
%A Mao, Rui
%A Zhang, Xulang
%A He, Liang
%A Cambria, Erik
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F xiao-etal-2024-vanessa
%X Prevailing research concentrates on superficial features or descriptions of images, revealing a significant gap in the systematic exploration of their connotative and aesthetic attributes. Furthermore, the use of cross-modal relation detection modules to eliminate noise from comprehensive image representations leads to the omission of subtle contextual information. In this paper, we present a Visual Connotation and Aesthetic Attributes Understanding Network (Vanessa) for Multimodal Aspect-based Sentiment Analysis. Concretely, Vanessa incorporates a Multi-Aesthetic Attributes Aggregation (MA3) module that models intra- and inter-dependencies among bi-modal representations as well as emotion-laden aesthetic attributes. Moreover, we devise a self-supervised contrastive learning framework to explore the pairwise relevance between images and text via the Gaussian distribution of their CLIP scores. By dynamically clustering and merging multi-modal tokens, Vanessa effectively captures both implicit and explicit sentimental cues. Extensive experiments on widely adopted two benchmarks verify Vanessa‘s effectiveness.
%R 10.18653/v1/2024.findings-emnlp.671
%U https://aclanthology.org/2024.findings-emnlp.671/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.671
%P 11486-11500
Markdown (Informal)
[Vanessa: Visual Connotation and Aesthetic Attributes Understanding Network for Multimodal Aspect-based Sentiment Analysis](https://aclanthology.org/2024.findings-emnlp.671/) (Xiao et al., Findings 2024)
ACL