不让任何文化掉队：ArtELingo-28，一个包含28种语言字幕的WikiArt基准数据集
No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages
AI总结：
本文提出ArtELingo-28，一个覆盖28种语言、约20万条注释的视觉语言基准，旨在促进跨文化与语言的图像情感字幕生成，并验证了文化相关性对跨语言迁移的积极作用。
摘要：
视觉与语言领域的研究得益于COCO等基准数据集而取得了显著进展。COCO字幕聚焦于英语中的明确事实；ArtEmis引入了主观情感，而ArtELingo引入了部分多语言性（中文和阿拉伯语）。然而，我们认为应该实现更多的多语言性。因此，我们提出了ArtELingo-28，一个跨越28种语言、包含约200,000条注释（每幅图像140条注释）的视觉语言基准数据集。传统上，视觉研究聚焦于明确的类别标签，而ArtELingo-28强调不同语言和文化间观点的多样性。挑战在于构建能够为图像分配情感字幕的机器学习系统。我们将针对三种新条件展示基线结果：零样本、少样本和一对全零样本。我们发现，对于文化相关的语言，跨语言迁移更为成功。数据和代码可在www.artelingo.org获取。
英文摘要：
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 $\textbf{28}$ languages and encompasses approximately $\textbf{200,000}$ annotations ($\textbf{140}$ 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 are provided at www.artelingo.org.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
