MouaffakAyoub/coco-arvqa

COCO-ARVQA是一个基于MS COCO 2017 train2017图像的阿拉伯语视觉问答数据集。它提供了阿拉伯语问题、阿拉伯语答案、答案列表、问题标识符、图像标识符和COCO图像文件名。该数据集不重新分发COCO图像，训练和验证拆分都引用了官方COCO 2017 train2017.zip存档中的图像。数据集旨在用于阿拉伯语视觉问答研究、多语言和阿拉伯语视觉语言建模、参数高效的多模态模型适配、低资源多模态学习研究以及阿拉伯语VQA系统的评估。

COCO-ARVQA is an Arabic Visual Question Answering dataset built over images from MS COCO 2017 train2017. It provides Arabic questions, Arabic answers, answer lists, question identifiers, image identifiers, and COCO image file names. This repository does not redistribute COCO images. Both the training and validation splits reference images from the official COCO 2017 train2017.zip archive. The dataset is intended for Arabic Visual Question Answering research, multilingual and Arabic vision-language modeling, parameter-efficient adaptation of multimodal models, low-resource multimodal learning research, and evaluation of Arabic VQA systems.