Automatic image captioning generation using deep learning

• Grant number: 18/09368-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): July 01, 2018
• Effective date (End): June 30, 2019
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Adriane Beatriz de Souza Serapião
• Grantee: Maynara Natalia Scoparo
• Host Institution: Instituto de Geociências e Ciências Exatas (IGCE). Universidade Estadual Paulista (UNESP). Campus de Rio Claro. Rio Claro , SP, Brazil

Abstract

Automatic image captioning generation is a task that consists of deciphering an image and describing it in natural language phrases. This task combines Natural Language Processing and computer Vision to generate captions. Recently, Deep Learning methods are achieving very promising results for the captions generation problem. This research proposes to investigate new combinations of convolutional neural networks over images and recurrent neural networks over sentences, aligning them with a structured objective to produce the textual description of an image. (AU)