AraImgStory-10K: An Arabic Image-Based Storytelling Dataset with Visual Elements, Emotion Labels, and Generated Stories
Abstract
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.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.