Boosting image captioning using ConvNeXt deep neural networks

This work proposes a ConvNeXt backbone-based model for image captioning. Specifically, the ConvNeXt convolutional model, a state-of-the-art computer vision architecture, is integrated with a long short-term memory network enclosing a visual attention module. Diverse experiments were performed to eva...

• Autore principale: Ramos Granda, Leo Thomas (author)
• Natura: bachelorThesis
• Lingua: eng
• Pubblicazione: 2023
• Soggetti: Redes neuronales artificiales; Visión computacional; Subtítulado de imágenes; Artificial neural networks; Computer vision; Image captioning
• Accesso online: http://repositorio.yachaytech.edu.ec/handle/123456789/627