Visual Question Answering for Peruvian Cuisine in Regional Spanish

Cosavalente M.R. · Proceedings of the AAAI Conference on Artificial Intelligence (2025) · DOI: 10.1609/aaai.v39i28.35339

Resumen

This project leverages Visual Question Answering (VQA) to promote Peruvian gastronomy by utilizing a culturally rich dataset and advanced models such as LLaVA-1.5 and GPT-2 Large. The evaluation will comprise both automated metrics and culinary expert assessments. This system addresses regional variations in dish names, promotes inclusivity by involving Peruvians from diverse regions in dataset construction, and enhances cultural representation. Copyright

Instituciones: Universidad Nacional de Trujillo