@inproceedings{99a1dc5747a04ca4bcca9d7c28b5776f,
title = "Dense Captioning of Natural Scenes in Spanish",
abstract = "The inclusion of visually impaired people to daily life is a challenging and active area of research. This work studies how to bring information about the surroundings to people delivered as verbal descriptions in Spanish using wearable devices. We use a neural network (DenseCap) for both identifying objects and generating phrases about them. DenseCap is running on a server to describe an image fed from a smartphone application, and its output is the text which a smartphone verbalizes. Our implementation achieves a mean Average Precision (mAP) of 5.0 in object recognition and quality of captions and takes an average of 7.5 s from the moment one grabs a picture until one receives the verbalization in Spanish.",
keywords = "Computer vision, Deep learning, Image captioning, Spanish language",
author = "Alejandro Gomez-Garay and Bogdan Raducanu and Joaqu{\'i}n Salas",
note = "Publisher Copyright: {\textcopyright} 2018, Springer International Publishing AG, part of Springer Nature.; 10th Mexican Conference on Pattern Recognition, MCPR 2018 ; Conference date: 27-06-2018 Through 30-06-2018",
year = "2018",
doi = "10.1007/978-3-319-92198-3_15",
language = "Ingl{\'e}s",
isbn = "9783319921976",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "145--154",
editor = "Martinez-Trinidad, {Jose Francisco} and Carrasco-Ochoa, {Jesus Ariel} and Olvera-Lopez, {Jose Arturo} and Sudeep Sarkar",
booktitle = "Pattern Recognition - 10th Mexican Conference, MCPR 2018, Proceedings",
address = "Alemania",
}