no code implementations • 13 Apr 2022 • Camila Kolling, Victor Araujo, Adriano Veloso, Soraia Raupp Musse
Hence, in this work, we introduce a novel learning method that combines both subjective human-based labels and objective annotations based on mathematical definitions of facial traits.
no code implementations • LREC 2020 • Caio L. M. Jeronimo, Claudio E. C. Campelo, Le Balby Marinho, ro, Allan Sales, Adriano Veloso, Roberta Viola
In this paper, we introduce a new set of lexicons for expressing subjectivity in text documents written in Brazilian Portuguese.
no code implementations • 30 Apr 2020 • Dehua Chen, Amir Jalilifard, Adriano Veloso, Nivio Ziviani
Once representations for drugs and diseases are obtained we learn the likelihood of new links (that is, new indications) between drugs and diseases.
no code implementations • 25 Apr 2020 • Eduardo Nigri, Nivio Ziviani, Fabio Cappabianco, Augusto Antunes, Adriano Veloso
Deep Convolutional Neural Networks (CNNs) are becoming prominent models for semi-automated diagnosis of Alzheimer's Disease (AD) using brain Magnetic Resonance Imaging (MRI).
no code implementations • 22 Apr 2020 • Dan Valle, Tiago Pimentel, Adriano Veloso
Thus, in this work we propose an objective measure to evaluate the reliability of explanations of deep models.
no code implementations • 21 Apr 2020 • Gianlucca Zuin, Adriano Veloso, João Cândido Portinari, Nivio Ziviani
To validate our method we build a model based on a weakly-supervised neural network for over $5{,}300$ paintings with hand-labeled descriptions made by experts for the paintings of the Brazilian painter Candido Portinari.
no code implementations • 23 Dec 2019 • Alison Marczewski, Adriano Veloso, Nívio Ziviani
We use transferable features to enable model adaptation from multiple source domains, given the sparseness of speech emotion data and the fact that target domains are short of labeled data.
no code implementations • 20 Dec 2019 • Tiago Alves, Alberto Laender, Adriano Veloso, Nivio Ziviani
Thus, mortality prediction models using patient data from a particular ICU population may perform suboptimally in other populations because the features used to train such models have different distributions across the groups.
no code implementations • ICLR 2019 • Tiago Pimentel, Marianne Monteiro, Juliano Viana, Adriano Veloso, Nivio Ziviani
This work presents a method for active anomaly detection which can be built upon existing deep learning solutions for unsupervised anomaly detection.
no code implementations • NAACL 2018 • Evelin Amorim, Marcia Can{\c{c}}ado, Adriano Veloso
We present features to quantify rater bias based on their comments, and we found that rater bias plays an important role in automated essay scoring.
no code implementations • 23 May 2018 • Tiago Pimentel, Marianne Monteiro, Adriano Veloso, Nivio Ziviani
Anomalies are intuitively easy for human experts to understand, but they are hard to define mathematically.
no code implementations • ICLR 2018 • Tiago Pimentel, Adriano Veloso, Nivio Ziviani
Representation learning is one of the foundations of Deep Learning and allowed important improvements on several Machine Learning tasks, such as Neural Machine Translation, Question Answering and Speech Recognition.
no code implementations • EACL 2017 • Evelin Amorim, Adriano Veloso
The AES system proposed employs several features already employed by AES systems for English language.