AraImgStory-10K: An Arabic Image-Based Storytelling Dataset with Visual Elements, Emotion Labels, and Generated Stories
收藏Zenodo2026-05-14 更新2026-05-26 收录
下载链接：
https://zenodo.org/doi/10.5281/zenodo.20176740
下载链接
链接失效反馈官方服务：
资源简介：
AraImgStory-10K is a custom dataset prepared for a Master's thesis project on retrieval-augmented multimodal story generation for Arabic image-based storytelling.
The dataset contains approximately 10,000 real images with extracted visual elements, emotion labels, generated Arabic stories, cleaned story texts, train/validation/test splits, a trained retriever model, a FAISS story index, and evaluation outputs.
The dataset supports research on Arabic image-based storytelling, multimodal learning, retrieval-augmented generation, Arabic natural language generation, and low-resource Arabic vision-language applications.
The archive includes Python scripts, processed dataset files, the trained retrieval model, FAISS index files, story metadata, and evaluation results.
提供机构：
Zenodo
创建时间：
2026-05-14
