@inproceedings{bhattacharyya-etal-2022-aligning,
title = "Aligning Images and Text with Semantic Role Labels for Fine-Grained Cross-Modal Understanding",
author = "Bhattacharyya, Abhidip and
Mauceri, Cecilia and
Palmer, Martha and
Heckman, Christoffer",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.528",
pages = "4944--4954",
abstract = "As vision processing and natural language processing continue to advance, there is increasing interest in multimodal applications, such as image retrieval, caption generation, and human-robot interaction. These tasks require close alignment between the information in the images and text. In this paper, we present a new multimodal dataset that combines state of the art semantic annotation for language with the bounding boxes of corresponding images. This richer multimodal labeling supports cross-modal inference for applications in which such alignment is useful. Our semantic representations, developed in the natural language processing community, abstract away from the surface structure of the sentence, focusing on specific actions and the roles of their participants, a level that is equally relevant to images. We then utilize these representations in the form of semantic role labels in the captions and the images and demonstrate improvements in standard tasks such as image retrieval. The potential contributions of these additional labels is evaluated using a role-aware retrieval system based on graph convolutional and recurrent neural networks. The addition of semantic roles into this system provides a significant increase in capability and greater flexibility for these tasks, and could be extended to state-of-the-art techniques relying on transformers with larger amounts of annotated data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharyya-etal-2022-aligning">
<titleInfo>
<title>Aligning Images and Text with Semantic Role Labels for Fine-Grained Cross-Modal Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhidip</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cecilia</namePart>
<namePart type="family">Mauceri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martha</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoffer</namePart>
<namePart type="family">Heckman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As vision processing and natural language processing continue to advance, there is increasing interest in multimodal applications, such as image retrieval, caption generation, and human-robot interaction. These tasks require close alignment between the information in the images and text. In this paper, we present a new multimodal dataset that combines state of the art semantic annotation for language with the bounding boxes of corresponding images. This richer multimodal labeling supports cross-modal inference for applications in which such alignment is useful. Our semantic representations, developed in the natural language processing community, abstract away from the surface structure of the sentence, focusing on specific actions and the roles of their participants, a level that is equally relevant to images. We then utilize these representations in the form of semantic role labels in the captions and the images and demonstrate improvements in standard tasks such as image retrieval. The potential contributions of these additional labels is evaluated using a role-aware retrieval system based on graph convolutional and recurrent neural networks. The addition of semantic roles into this system provides a significant increase in capability and greater flexibility for these tasks, and could be extended to state-of-the-art techniques relying on transformers with larger amounts of annotated data.</abstract>
<identifier type="citekey">bhattacharyya-etal-2022-aligning</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.528</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4944</start>
<end>4954</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Images and Text with Semantic Role Labels for Fine-Grained Cross-Modal Understanding
%A Bhattacharyya, Abhidip
%A Mauceri, Cecilia
%A Palmer, Martha
%A Heckman, Christoffer
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F bhattacharyya-etal-2022-aligning
%X As vision processing and natural language processing continue to advance, there is increasing interest in multimodal applications, such as image retrieval, caption generation, and human-robot interaction. These tasks require close alignment between the information in the images and text. In this paper, we present a new multimodal dataset that combines state of the art semantic annotation for language with the bounding boxes of corresponding images. This richer multimodal labeling supports cross-modal inference for applications in which such alignment is useful. Our semantic representations, developed in the natural language processing community, abstract away from the surface structure of the sentence, focusing on specific actions and the roles of their participants, a level that is equally relevant to images. We then utilize these representations in the form of semantic role labels in the captions and the images and demonstrate improvements in standard tasks such as image retrieval. The potential contributions of these additional labels is evaluated using a role-aware retrieval system based on graph convolutional and recurrent neural networks. The addition of semantic roles into this system provides a significant increase in capability and greater flexibility for these tasks, and could be extended to state-of-the-art techniques relying on transformers with larger amounts of annotated data.
%U https://aclanthology.org/2022.lrec-1.528
%P 4944-4954
Markdown (Informal)
[Aligning Images and Text with Semantic Role Labels for Fine-Grained Cross-Modal Understanding](https://aclanthology.org/2022.lrec-1.528) (Bhattacharyya et al., LREC 2022)
ACL