Please use this identifier to cite or link to this item:
http://hdl.handle.net/10609/100446
Title: | Deep learning for image captioning: an encoder-decoder architecture with soft attention |
Author: | Gómez Martínez, Mario |
Director: | Casas-Roma, Jordi |
Tutor: | Bosch Rue, Anna |
Abstract: | Automatic image captioning, the task of automatically producing a natural-language description for an image, has the potential to assist those with visual impairments by explaining images using text-to-speech systems. However, accurate image captioning is a challenging task that requires integrating and pushing further the latest improvements at the intersection of computer vision and natural language processing fields This work aims at building an advanced model based on neural networks and deep learning for the automated generation of image captions. |
Keywords: | image captioning deep learning artificial neural networks |
Document type: | info:eu-repo/semantics/masterThesis |
Issue Date: | 28-Jun-2019 |
Publication license: | http://creativecommons.org/licenses/by-nc-sa/3.0/es/ |
Appears in Collections: | Bachelor thesis, research projects, etc. |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
magomarTFM0619memory.pdf | Memory of TFM | 7,85 MB | Adobe PDF | View/Open |
Share:
This item is licensed under a Creative Commons License