no code implementations • ECCV 2020 • Robert Mendel, Luis Antonio de Souza Jr, David Rauber, João Paulo Papa, Christoph Palm
Apart from the supervised training on the labeled data, the segmentation network is judged by an additional network.
1 code implementation • 11 Feb 2024 • Leandro A. Passos, Douglas Rodrigues, Danilo Jodas, Kelton A. P. Costa, Ahsan Adeel, João Paulo Papa
This paper presents BioNeRF, a biologically plausible architecture that models scenes in a 3D representation and synthesizes new views through radiance fields.
no code implementations • 5 Jan 2024 • Gabriel Lino Garcia, Pedro Henrique Paiola, Luis Henrique Morelli, Giovani Candido, Arnaldo Cândido Júnior, Danilo Samuel Jodas, Luis C. S. Afonso, Ivan Rizzo Guilherme, Bruno Elias Penteado, João Paulo Papa
Large Language Models (LLMs) are increasingly bringing advances to Natural Language Processing.
no code implementations • 20 Oct 2023 • Mateus Roder, Leandro Aparecido Passos, João Paulo Papa, André Luis Debiaso Rossi
The predictive performance of the model was compared against five baseline methods as well as a random search, performing either ANN hyperparameter tuning and feature selection.
no code implementations • 22 Jul 2023 • Nícolas Barbosa Gomes, Arissa Yoshida, Mateus Roder, Guilherme Camargo de Oliveira, João Paulo Papa
Identifying Amyotrophic Lateral Sclerosis (ALS) in its early stages is essential for establishing the beginning of treatment, enriching the outlook, and enhancing the overall well-being of those affected individuals.
no code implementations • 21 Dec 2022 • Vinícius Camargo da Silva, João Paulo Papa, Kelton Augusto Pontara da Costa
Automatic Text Summarization (ATS) is becoming relevant with the growth of textual data; however, with the popularization of public large-scale datasets, some recent machine learning approaches have focused on dense models and architectures that, despite producing notable results, usually turn out in models difficult to interpret.
no code implementations • 20 Dec 2022 • Gustavo Henrique de Rosa, João Paulo Papa
This work presents a thorough review concerning recent studies and text generation advancements using Generative Adversarial Networks.
1 code implementation • 19 Dec 2022 • Gustavo H. de Rosa, Mateus Roder, João Paulo Papa, Claudio F. G. dos Santos
Machine Learning algorithms have been extensively researched throughout the last decade, leading to unprecedented advances in a broad range of applications, such as image classification and reconstruction, object recognition, and text categorization.
1 code implementation • 26 Sep 2022 • Danilo Samuel Jodas, Leandro Aparecido Passos, Ahsan Adeel, João Paulo Papa
Demands for minimum parameter setup in machine learning models are desirable to avoid time-consuming optimization processes.
no code implementations • 6 Jun 2022 • Leandro A. Passos, João Paulo Papa, Amir Hussain, Ahsan Adeel
Despite the recent success of machine learning algorithms, most models face drawbacks when considering more complex tasks requiring interaction between different sources, such as multimodal input data and logical time sequences.
1 code implementation • Computer Methods and Programs in Biomedicine 2022 • Rishav Pramanik, Momojit Biswas, ShibaprasadSen, Luis Antonio de Souza Júnior, João Paulo Papa, Ram Sarkar
This article proposes a fuzzy distance-based ensemble approach composed of deep learning models for cervical cancer detection in PaP smear images.
Ranked #1 on Image Classification on HErlev
1 code implementation • 17 Feb 2022 • Leandro Aparecido Passos, Danilo S. Jodas, Luiz C. F. Ribeiro, Marco Akio, Andre Nunes de Souza, João Paulo Papa
Such a behavior yields considerable influence on the machine learning model's performance since it becomes biased on the more frequent data it receives.
no code implementations • 12 Feb 2022 • Leandro A. Passos, Danilo Jodas, Kelton A. P. da Costa, Luis A. Souza Júnior, Douglas Rodrigues, Javier Del Ser, David Camacho, João Paulo Papa
Recent advancements in deep learning generative models have raised concerns as they can create highly convincing counterfeit images and videos.
no code implementations • 9 Feb 2022 • Leandro Aparecido Passos, João Paulo Papa, Javier Del Ser, Amir Hussain, Ahsan Adeel
Our proposed AV CCA-GNN model deals with multimodal representation learning context.
1 code implementation • 8 Feb 2022 • Gustavo Henrique de Rosa, Mateus Roder, João Paulo Papa
Machine Learning has attracted considerable attention throughout the past decade due to its potential to solve far-reaching tasks, such as image classification, object recognition, anomaly detection, and data forecasting.
no code implementations • 10 Jan 2022 • Claudio Filipi Gonçalves dos Santos, João Paulo Papa
The works are classified into three main areas: the first one is called "data augmentation", where all the techniques focus on performing changes in the input data.
no code implementations • 10 Jan 2022 • Claudio Filipi Gonçalves dos Santos, Diego de Souza Oliveira, Leandro A. Passos, Rafael Gonçalves Pires, Daniel Felipe Silva Santos, Lucas Pascotti Valem, Thierry P. Moreira, Marcos Cleison S. Santana, Mateus Roder, João Paulo Papa, Danilo Colombo
In general, biometry-based control systems may not rely on individual expected behavior or cooperation to operate appropriately.
1 code implementation • 23 Dec 2021 • Gonzalo Nápoles, Isel Grau, Leonardo Concepción, Lisa Koutsoviti Koumeri, João Paulo Papa
This paper presents a Fuzzy Cognitive Map model to quantify implicit bias in structured datasets where features can be numeric or discrete.
1 code implementation • 6 Sep 2021 • Lucas Fernando Alvarenga e Silva, Daniel Carlos Guimarães Pedronette, Fábio Augusto Faria, João Paulo Papa, Jurandy Almeida
Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks.
Multi-Source Unsupervised Domain Adaptation Unsupervised Domain Adaptation
1 code implementation • 22 Jun 2021 • Gustavo H. de Rosa, João Paulo Papa
A graph-inspired classifier, known as Optimum-Path Forest (OPF), has proven to be a state-of-the-art algorithm comparable to Logistic Regressors, Support Vector Machines in a wide variety of tasks.
no code implementations • 17 Jan 2021 • Mateus Roder, Leandro A. Passos, Luiz Carlos Felix Ribeiro, Clayton Pereira, João Paulo Papa
With the advent of deep learning, the number of works proposing new methods or improving existent ones has grown exponentially in the last years.
no code implementations • 17 Jan 2021 • Mateus Roder, Leandro A. Passos, Luiz Carlos Felix Ribeiro, Barbara Caroline Benato, Alexandre Xavier Falcão, João Paulo Papa
Currently, approximately $4$ billion people are infected by intestinal parasites worldwide.
no code implementations • 14 Jan 2021 • Leandro Aparecido Passos, João Paulo Papa
Deep learning techniques, such as Deep Boltzmann Machines (DBMs), have received considerable attention over the past years due to the outstanding results concerning a variable range of domains.
no code implementations • 14 Jan 2021 • Gustavo H. de Rosa, João Paulo Papa, Xin-She Yang
The essential idea behind it is to find the most suitable subset of features according to some criterion.
2 code implementations • 27 Jul 2020 • Claudio Filipi Goncalves do Santos, Danilo Colombo, Mateus Roder, João Paulo Papa
Different techniques have emerged in the deep learning scenario, such as Convolutional Neural Networks, Deep Belief Networks, and Long Short-Term Memory Networks, to cite a few.
1 code implementation • 16 Mar 2020 • Mateus Roder, Gustavo Henrique de Rosa, João Paulo Papa
Throughout the last years, machine learning techniques have been broadly encouraged in the context of deep learning architectures.
1 code implementation • 28 Jan 2020 • Gustavo Henrique de Rosa, João Paulo Papa, Alexandre Xavier Falcão
Machine learning techniques have been paramount throughout the last years, being applied in a wide range of tasks, such as classification, object recognition, person identification, and image segmentation.
no code implementations • 19 Jun 2018 • Gustavo Botelho de Souza, João Paulo Papa, Aparecido Nilceu Marana
However, these methods do not consider the importance of learning deep local features from each facial region, even though it is known from face recognition that each facial region presents different visual aspects, which can also be exploited for face spoofing detection.