no code implementations • 15 Jun 2021 • Luis Felipe Henriques, Sérgio Colcher, Ruy Luiz Milidiú, André Bulcão, Pablo Barros
Our method uses deep learning models to generate pairs of seismic image patches and their respective salt masks for the Data Augmentation.
no code implementations • 30 Nov 2020 • Luis Felipe M. O. Henriques, Eduardo Morgan, Sergio Colcher, Ruy Luiz Milidiú
We train and evaluate our proposed model in a publicly available dataset composed of power demand measures from a poultry feed factory located in Brazil.
no code implementations • 23 Jul 2020 • Ruy Luiz Milidiú, Luis Felipe Müller
In this work, we propose the SeismoFlow a flow-based generative model to create synthetic samples, aiming to address the class imbalance.
no code implementations • 7 May 2020 • Antonio José G. Busson, Sérgio Colcher, Ruy Luiz Milidiú, Bruno Pereira Dias, André Bulcão
Herein, we describe the following: (1) the construction of a real-world dataset of seismic noise localization based on 6, 500 seismograms; (2) a multi-scale feature-fusion-based detector that uses the MobileNet combined with the Feature Pyramid Net as the backbone; and (3) the Single Shot multi-box detector for box classification/regression.
no code implementations • 3 Dec 2019 • Eduardo Betine Bucker, Antonio José Grandson Busson, Ruy Luiz Milidiú, Sérgio Colcher, Bruno Pereira Dias, André Bulcão
Deep Learning-based models such as Convolutional Neural Networks, have led to significant advancements in several areas of computing applications.
no code implementations • 25 Nov 2019 • Ruy Luiz Milidiú, Rafael Henrique Santos Rocha
Furthermore, we provide mistake bounds for each one of the two online algorithms.
no code implementations • 10 Nov 2019 • Pedro V. A. de Freitas, Paulo R. C. Mendes, Gabriel N. P. dos Santos, Antonio José G. Busson, Álan Livio Guedes, Sérgio Colcher, Ruy Luiz Milidiú
More than telling if a video is either appropriate or inappropriate, it is also important to identify which parts of it contain such content, for preserving parts that would be discarded in a simple broad analysis.
no code implementations • 13 Aug 2019 • Daniel Specht Menezes, Pedro Savarese, Ruy Luiz Milidiú
With the recent progress in machine learning, boosted by techniques such as deep learning, many tasks can be successfully solved once a large enough dataset is available for training.