swap-uniba/OK-VQA_IT

---
dataset_info:
features:
- name: image
dtype: image
- name: id
dtype: string
- name: question
dtype: string
- name: answers
sequence: string
splits:
- name: val2014
num_bytes: 1611077750.72
num_examples: 3260
download_size: 1591120019
dataset_size: 1611077750.72
configs:
- config_name: default
data_files:
- split: val2014
path: data/val2014-*
---

# Dataset Card for OK-VQA_IT

## Dataset description

This is a formatted version of [OK-VQA](https://okvqa.allenai.org/) translated to the Italian language using [MADLAD400](https://huggingface.co/google/madlad400-3b-mt).

## Citation

If you use this dataset in your research you should cite both of the following:

```
@inproceedings{musacchioLLaVANDiNO,
title={LLaVA-NDiNO: Empowering LLMs with Multimodality for the Italian Language},
author={Musacchio, Elio and Siciliani, Lucia and Basile, Pierpaolo and Semeraro, Giovanni},
booktitle={Proceedings of the Eighth Workshop on Natural Language for Artificial Intelligence (NL4AI 2024) co-located with 23th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2024)},
year={2024}
}

@InProceedings{okvqa,
author = {Kenneth Marino and Mohammad Rastegari and Ali Farhadi and Roozbeh Mottaghi},
title = {OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge},
booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2019},
}
```