@inproceedings{nag-chowdhury-etal-2021-sandi,
title = "{SANDI}: Story-and-Images Alignment",
author = "Nag Chowdhury, Sreyasi and
Razniewski, Simon and
Weikum, Gerhard",
editor = "Merlo, Paola and
Tiedemann, Jorg and
Tsarfaty, Reut",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-main.85",
doi = "10.18653/v1/2021.eacl-main.85",
pages = "989--999",
abstract = "The Internet contains a multitude of social media posts and other of stories where text is interspersed with images. In these contexts, images are not simply used for general illustration, but are judiciously placed in certain spots of a story for multimodal descriptions and narration. In this work we analyze the problem of text-image alignment, and present SANDI, a methodology for automatically selecting images from an image collection and aligning them with text paragraphs of a story. SANDI combines visual tags, user-provided tags and background knowledge, and uses an Integer Linear Program to compute alignments that are semantically meaningful. Experiments show that SANDI can select and align images with texts with high quality of semantic fit.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nag-chowdhury-etal-2021-sandi">
<titleInfo>
<title>SANDI: Story-and-Images Alignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sreyasi</namePart>
<namePart type="family">Nag Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Razniewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerhard</namePart>
<namePart type="family">Weikum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paola</namePart>
<namePart type="family">Merlo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Internet contains a multitude of social media posts and other of stories where text is interspersed with images. In these contexts, images are not simply used for general illustration, but are judiciously placed in certain spots of a story for multimodal descriptions and narration. In this work we analyze the problem of text-image alignment, and present SANDI, a methodology for automatically selecting images from an image collection and aligning them with text paragraphs of a story. SANDI combines visual tags, user-provided tags and background knowledge, and uses an Integer Linear Program to compute alignments that are semantically meaningful. Experiments show that SANDI can select and align images with texts with high quality of semantic fit.</abstract>
<identifier type="citekey">nag-chowdhury-etal-2021-sandi</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-main.85</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-main.85</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>989</start>
<end>999</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SANDI: Story-and-Images Alignment
%A Nag Chowdhury, Sreyasi
%A Razniewski, Simon
%A Weikum, Gerhard
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F nag-chowdhury-etal-2021-sandi
%X The Internet contains a multitude of social media posts and other of stories where text is interspersed with images. In these contexts, images are not simply used for general illustration, but are judiciously placed in certain spots of a story for multimodal descriptions and narration. In this work we analyze the problem of text-image alignment, and present SANDI, a methodology for automatically selecting images from an image collection and aligning them with text paragraphs of a story. SANDI combines visual tags, user-provided tags and background knowledge, and uses an Integer Linear Program to compute alignments that are semantically meaningful. Experiments show that SANDI can select and align images with texts with high quality of semantic fit.
%R 10.18653/v1/2021.eacl-main.85
%U https://aclanthology.org/2021.eacl-main.85
%U https://doi.org/10.18653/v1/2021.eacl-main.85
%P 989-999
Markdown (Informal)
[SANDI: Story-and-Images Alignment](https://aclanthology.org/2021.eacl-main.85) (Nag Chowdhury et al., EACL 2021)
ACL
- Sreyasi Nag Chowdhury, Simon Razniewski, and Gerhard Weikum. 2021. SANDI: Story-and-Images Alignment. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 989–999, Online. Association for Computational Linguistics.