@inproceedings{mohamed-etal-2024-culture,
title = "No Culture Left Behind: {A}rt{EL}ingo-28, a Benchmark of {W}iki{A}rt with Captions in 28 Languages",
author = "Mohamed, Youssef and
Li, Runjia and
Ahmad, Ibrahim and
Haydarov, Kilichbek and
Torr, Philip and
Church, Kenneth and
Elhoseiny, Mohamed",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.1165",
pages = "20939--20962",
abstract = "Research in vision and language has made considerable progress thanks to benchmarks such as COCO. COCO captions focused on unambiguous facts in English; ArtEmis introduced subjective emotions and ArtELingo introduced some multilinguality (Chinese and Arabic). However we believe there should be more multilinguality. Hence, we present ArtELingo-28, a vision-language benchmark that spans 28 languages and encompasses approximately 200,000 annotations (140 annotations per image). Traditionally, vision research focused on unambiguous class labels, whereas ArtELingo-28 emphasizes diversity of opinions over languages and cultures. The challenge is to build machine learning systems that assign emotional captions to images. Baseline results will be presented for three novel conditions: Zero-Shot, Few-Shot and One-vs-All Zero-Shot. We find that cross-lingual transfer is more successful for culturally-related languages. Data and code will be made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-etal-2024-culture">
<titleInfo>
<title>No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Youssef</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runjia</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Ahmad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kilichbek</namePart>
<namePart type="family">Haydarov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Torr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenneth</namePart>
<namePart type="family">Church</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Elhoseiny</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>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</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>Research in vision and language has made considerable progress thanks to benchmarks such as COCO. COCO captions focused on unambiguous facts in English; ArtEmis introduced subjective emotions and ArtELingo introduced some multilinguality (Chinese and Arabic). However we believe there should be more multilinguality. Hence, we present ArtELingo-28, a vision-language benchmark that spans 28 languages and encompasses approximately 200,000 annotations (140 annotations per image). Traditionally, vision research focused on unambiguous class labels, whereas ArtELingo-28 emphasizes diversity of opinions over languages and cultures. The challenge is to build machine learning systems that assign emotional captions to images. Baseline results will be presented for three novel conditions: Zero-Shot, Few-Shot and One-vs-All Zero-Shot. We find that cross-lingual transfer is more successful for culturally-related languages. Data and code will be made publicly available.</abstract>
<identifier type="citekey">mohamed-etal-2024-culture</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.1165</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>20939</start>
<end>20962</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages
%A Mohamed, Youssef
%A Li, Runjia
%A Ahmad, Ibrahim
%A Haydarov, Kilichbek
%A Torr, Philip
%A Church, Kenneth
%A Elhoseiny, Mohamed
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F mohamed-etal-2024-culture
%X Research in vision and language has made considerable progress thanks to benchmarks such as COCO. COCO captions focused on unambiguous facts in English; ArtEmis introduced subjective emotions and ArtELingo introduced some multilinguality (Chinese and Arabic). However we believe there should be more multilinguality. Hence, we present ArtELingo-28, a vision-language benchmark that spans 28 languages and encompasses approximately 200,000 annotations (140 annotations per image). Traditionally, vision research focused on unambiguous class labels, whereas ArtELingo-28 emphasizes diversity of opinions over languages and cultures. The challenge is to build machine learning systems that assign emotional captions to images. Baseline results will be presented for three novel conditions: Zero-Shot, Few-Shot and One-vs-All Zero-Shot. We find that cross-lingual transfer is more successful for culturally-related languages. Data and code will be made publicly available.
%U https://aclanthology.org/2024.emnlp-main.1165
%P 20939-20962
Markdown (Informal)
[No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages](https://aclanthology.org/2024.emnlp-main.1165) (Mohamed et al., EMNLP 2024)
ACL
- Youssef Mohamed, Runjia Li, Ibrahim Ahmad, Kilichbek Haydarov, Philip Torr, Kenneth Church, and Mohamed Elhoseiny. 2024. No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 20939–20962, Miami, Florida, USA. Association for Computational Linguistics.