neulab/PangeaBench-xm100

---
language:
- ar
- bn
- cs
- da
- de
- el
- en
- es
- fa
- fi
- fil
- fr
- hi
- hr
- hu
- id
- it
- he
- ja
- ko
- mi
- nl
- 'no'
- pl
- pt
- quz
- ro
- ru
- sv
- sw
- te
- th
- tr
- uk
- vi
- zh
license: cc-by-4.0
size_categories:
- 1K<n<10K
task_categories:
- image-to-text
pretty_name: xm100
dataset_info:
features:
- name: image_id
dtype: string
- name: image_locale
dtype: string
- name: caption
dtype: string
- name: image
dtype: image
splits:
- name: ar
num_examples: 100
- name: bn
num_examples: 100
- name: cs
num_examples: 100
- name: da
num_examples: 100
- name: de
num_examples: 100
- name: el
num_examples: 100
- name: en
num_examples: 100
- name: es
num_examples: 100
- name: fa
num_examples: 100
- name: fi
num_examples: 100
- name: fil
num_examples: 100
- name: fr
num_examples: 100
- name: hi
num_examples: 100
- name: hr
num_examples: 100
- name: hu
num_examples: 100
- name: id
num_examples: 100
- name: it
num_examples: 100
- name: he
num_examples: 100
- name: ja
num_examples: 100
- name: ko
num_examples: 100
- name: mi
num_examples: 100
- name: nl
num_examples: 100
- name: 'no'
num_examples: 100
- name: pl
num_examples: 100
- name: pt
num_examples: 100
- name: quz
num_examples: 100
- name: ro
num_examples: 100
- name: ru
num_examples: 100
- name: sv
num_examples: 100
- name: sw
num_examples: 100
- name: te
num_examples: 100
- name: th
num_examples: 100
- name: tr
num_examples: 100
- name: uk
num_examples: 100
- name: vi
num_examples: 100
- name: zh
num_examples: 100
configs:
- config_name: default
data_files:
- split: ar
path: data/ar-*
- split: bn
path: data/bn-*
- split: cs
path: data/cs-*
- split: da
path: data/da-*
- split: de
path: data/de-*
- split: el
path: data/el-*
- split: en
path: data/en-*
- split: es
path: data/es-*
- split: fa
path: data/fa-*
- split: fi
path: data/fi-*
- split: fil
path: data/fil-*
- split: fr
path: data/fr-*
- split: hi
path: data/hi-*
- split: hr
path: data/hr-*
- split: hu
path: data/hu-*
- split: id
path: data/id-*
- split: it
path: data/it-*
- split: he
path: data/he-*
- split: ja
path: data/ja-*
- split: ko
path: data/ko-*
- split: mi
path: data/mi-*
- split: nl
path: data/nl-*
- split: 'no'
path: data/no-*
- split: pl
path: data/pl-*
- split: pt
path: data/pt-*
- split: quz
path: data/quz-*
- split: ro
path: data/ro-*
- split: ru
path: data/ru-*
- split: sv
path: data/sv-*
- split: sw
path: data/sw-*
- split: te
path: data/te-*
- split: th
path: data/th-*
- split: tr
path: data/tr-*
- split: uk
path: data/uk-*
- split: vi
path: data/vi-*
- split: zh
path: data/zh-*
---

# XM100

### This is a copy from https://google.github.io/crossmodal-3600/

If you use this dataset, please cite the original authors:
```bibtex
@inproceedings{ThapliyalCrossmodal2022,
author = {Ashish Thapliyal and Jordi Pont-Tuset and Xi Chen and Radu Soricut},
title = {{Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset}},
booktitle = {EMNLP},
year = {2022}
}
```