Search

Your search keyword '"Ríos, Gastón"' showing total 7 results
Start Over Author "Ríos, Gastón"
7 results on '"Ríos, Gastón"'

2. LSA-T: The first continuous Argentinian Sign Language dataset for Sign Language Translation

Author

Bianco, Pedro Dal, Ríos, Gastón, Ronchetti, Franco, Quiroga, Facundo, Stanchi, Oscar, Hasperué, Waldo, and Rosete, Alejandro

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Sign language translation (SLT) is an active field of study that encompasses human-computer interaction, computer vision, natural language processing and machine learning. Progress on this field could lead to higher levels of integration of deaf people. This paper presents, to the best of our knowledge, the first continuous Argentinian Sign Language (LSA) dataset. It contains 14,880 sentence level videos of LSA extracted from the CN Sordos YouTube channel with labels and keypoints annotations for each signer. We also present a method for inferring the active signer, a detailed analysis of the characteristics of the dataset, a visualization tool to explore the dataset and a neural SLT model to serve as baseline for future experiments., Comment: Accepted at IBERAMIA 2022. Dataset download info at https://github.com/midusi/LSA-T

Published
2022

3. LSA-T: The First Continuous Argentinian Sign Language Dataset for Sign Language Translation

Author

Dal Bianco, Pedro, Ríos, Gastón, Ronchetti, Franco, Quiroga, Facundo, Stanchi, Oscar, Hasperué, Waldo, Rosete, Alejandro, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Bicharra Garcia, Ana Cristina, editor, Ferro, Mariza, editor, and Rodríguez Ribón, Julio Cesar, editor

Published
2022
Full Text
View/download PDF

4. A Comparison of Neural Networks for Sign Language Recognition with LSA64

Author

Mindlin, Iván, Quiroga, Facundo, Ronchetti, Franco, Bianco, Pedro Dal, Ríos, Gastón, Lanzarini, Laura, Hasperué, Waldo, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Naiouf, Marcelo, editor, Rucci, Enzo, editor, Chichizola, Franco, editor, and De Giusti, Laura, editor

Published
2021
Full Text
View/download PDF

6. A study on pose-based deep learning models for gloss-free Sign Language Translation.

Author

Bianco, Pedro Dal, Ríos, Gastón, Hasperué, Waldo, Stanchi, Oscar, Quiroga, Facundo, and Ronchetti, Franco

Subjects
SIGN language, DEEP learning, GREEK language, DATA reduction, MODELS & modelmaking
Abstract

Copyright of Journal of Computer Science & Technology (JCS&T) is the property of Journal of Computer Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Published
2024
Full Text
View/download PDF

7. Clasificación de gestos utilizando Deep Learning en datasets con pocos datos etiquetados

Author

Ríos, Gastón Gustavo, Ronchetti, Franco, and Hasperué, Waldo

Subjects
Deep Learning, Visión por computadora, Conjuntos de datos, Lengua de señas, Ciencias Informáticas, Gestos
Abstract

En los últimos años el aprendizaje profundo ha demostrado ser un método suma-mente efectivo a la hora de realizar clasificación de imágenes. Esta efectividad esasociada en parte al aumento de poder de procesamiento, al desarrollo de nuevos al-goritmos y al incremento en el tamaño y cantidad de conjuntos de datos disponibles.Pero este aumento en la cantidad de conjuntos de datos disponibles no ha alcanzadotodas las problemáticas existentes, teniendo múltiples áreas donde los conjuntos dedatos disponibles son pequeños para la aplicación efectiva de modelos de aprendiza-je profundo o cuyos datos poseen información poco útil al no ser lo suficientementerepresentativa del problema o poseer ruido.Esta limitación en la cantidad de datos etiquetados es una problemática actualexistente en la clasificación de señas de la lengua de señas. En esta tesis se explorarondiversos métodos para lograr alcanzar la mejor precisión posible utilizando la menorcantidad de datos. Llegando finalmente a lograr una precisión en la clasificación deseñas estáticas del 99.26 % en el conjunto de datos LSA16 y 94 % con el conjunto dedatos RWTH-PHOENIX-Wheater., Facultad de Informática

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results