Publications

Theses and Dissertations

Investigating pooling in graph neural networks for cancer genomics classification and the generalizability of pan-cancer models to cancer-specific predictions
Master's Dissertation in Computer Science, UFRGS, 2023
Thomas V. Fontanari, Mariana Recamonde-Mendoza
Dissertation
Simultaneous magnification of subtle motions and color variations in videos using riesz pyramids
Bachelor's Thesis in Computer Engineering, UFRGS, 2021
Thomas V. Fontanari, Manuel M. Oliveira
Thesis

Journal Papers

Simultaneous magnification of subtle motions and color variations in videos using Riesz pyramids
Computers & Graphics, 2021
Thomas V. Fontanari, Manuel M. Oliveira
Paper Code
A Fast Monolithic 8-2 Adder Compressor Circuit
Journal of Integrated Circuits and Systems (JICS), 2019
Thomas V. Fontanari, Guilherme Paim, Leandro M. G. Rocha, Gustavo M. Santana, Eduardo A. C. da Costa, Sergio Bampi
Paper

Conference Papers

Evaluating the Generalization of Neural Network-Based Pan-Cancer Classification Models for Cohort-Specific Predictions
Brazilian Symposium on Bioinformatics (BSB), 2024
Thomas V. Fontanari, Mariana Recamonde-Mendoza
Paper Code
Cross-validation Strategies for Balanced and Imbalanced Datasets
Brazillian Conference on Intelligent Systems (BRACIS), 2022
Thomas V. Fontanari, Tiago Comassetto Fróes, Mariana Recamonde-Mendoza
Paper Code
Study on the Complexity of Omics Data: An Analysis for Cancer Survival Prediction
Brazilian Symposium on Bioinformatics (BSB), 2022
Carlos Daniel Andrade, Thomas V. Fontanari, Mariana Recamonde-Mendoza
Paper
An Efficient N-bit 8-2 Adder Compressor with a Constant Internal Carry Propagation Delay
Latin American Symposium on Circuits and Systems (LASCAS), 2020
Thomas V. Fontanari, Guilherme Paim, Leandro MG Rocha, Patricia Ucker, Eduardo AC da Costa, Sergio Bampi
Paper
Investigating the Impact of Pruning on Energy-Accuracy of Neural Networks
ICCEEg, 2020
Thomas V. Fontanari, Leandro MG Rocha, Gustavo M Santana, Guilherme Paim, Eduardo AC Da Costa, Sergio Bampi
PDF
Selected for publication as one of the best undergraduate-level works presented at SIM
Exploring motion vector cost with partial distortion elimination in sum of absolute differences for HEVC integer motion estimation
IEEE International New Circuits and Systems Conference (NEWCAS), 2019
Brunno Abreu, Mateus Grellert, Guilherme Paim, Thomas V. Fontanari, Leandro MG Rocha, Eduardo AC Da Costa, Sergio Bampi
Paper