Thiago M. Paixão

Thiago M. Paixão is a Brazilian researcher and Associate Professor of Computer Science at the Federal Institute of Espírito Santo (IFES). His career combines applied research and teaching in artificial intelligence, with expertise in computer vision and, more recently, natural language processing. He holds a Ph.D. in Computer Science from the Federal University of Espírito Santo (UFES), during which he worked as a visiting researcher at the École de Technologie Supérieure in Montreal, Canada.

At IFES, Thiago advises research in the Applied Computing graduate program and teaches in the Bachelor’s program in Information Systems. His current research interests include Large Language Models (LLMs), Visual Language Models (VLMs), self-supervised learning, and emotional analysis applied to mental health.

DOWNLOAD CV

Innovation Boosted by

AI Projects

2024 — Present

Research Coordinator

Facial Analysis in Selfies to Identify Anxiety and Depression in Pregnant Patients

This project aims to develop an AI system to detect anxiety and depression in pregnant women by using selfies and self-assessment questionnaires to train predictive models, specifically aiming for authentic facial expression analysis outside controlled environments, as part of the Grávida Digital macroproject.

2024 — Present

Research Coordinator

Identifying Anxiety and Depression Using Facial Analysis in a Reduced Database

This research explores innovative methods to identify depression and anxiety through facial expression analysis in selfies, employing transfer learning and OpenFace for feature extraction, investigating fake smile detection, and planning to develop a mobile application to collect passive selfie data, while addressing small database challenges.

2024 — Present

Research Coordinator

Text-To-SQL Solutions for IAGROGPT: An Intelligent Virtual Assistant for Brazilian Agriculture

This project is dedicated to developing Text-to-SQL solutions for IAGROGPT, an intelligent virtual assistant specifically designed for the Brazilian agribusiness sector.

2023 — 2024

Research Coordinator

Air Writing Using Computer Vision and Machine Learning

This concluded research project centered on "Air Writing", leveraging computer vision and machine learning techniques to recognize text and detect writing intention, also developing the computer vision algorithm for electronic pens and points of interest.

2022 — 2024

Research Coordinator

Blast Furnace Temperature Prediction Using Machine Learning

This project aimed to enhance blast furnace temperature control in a steel mill using AI to predict multi-step ahead temperatures, replacing manual monitoring to reduce pollutant emissions, production costs, and production stoppages while improving pig iron quality by enabling continuous monitoring and anticipatory adjustments.

2022 — 2024

Senior AI Researcher

Visual Classifier Training Process Using Reduced Databases

This research focused on the training process of visual classifiers when utilizing reduced databases, which included enhancing classification models with data and generating databases using internet data.

2021 — Present

AI Researcher

Institute of Applied Computational Intelligence - I2CA

The I2CA's mission is to conduct research in applied computational intelligence for industry, emphasizing autonomous vehicles and intelligent systems, training specialized personnel, and fortifying the AI business ecosystem by researching Artificial Visual Cognition and developing powerful Autonomous Computational Intelligences (ICAs) through macroprojects in collaboration with various partners to create new technologies.

2020 — Present

Research Coordinator

Grávida Digital - Development of mobile-based software to identify depression, anxiety, and stress during pregnancy

The core objective of this project is to develop an algorithm to identify depression, anxiety, and stress in pregnant women by using voice biomarker technology, facial expression analysis, cell phone usage patterns, metadata, data mining, and artificial intelligence, involving partnerships with several universities.

2021 — Present

Coordinator

UniversidadES - Open University Program of Espírito Santo (UnAC) of the UniversidadES System

This is a teaching project that forms part of the UniversidadES - Open University Program of Espírito Santo (UnAC) of the UniversidadES System.

2022 — 2022

AI Researcher

DeepRec-PRL22

This is an unregistered software program related to the doctoral research on reconstructing shredded documents using deep learning, which involved exploring character shapes and developing a deep learning-based compatibility score for reconstruction.

Knowledge and Discovery Registered in

Research Papers

2025
2024
2022
2021
2020
2019
2018
2008

Automatic multiple-choice question generation and evaluation systems based on LLM: A study case with university resolutions

SS Mucciaccia, TM Paixão, FW Mutz, CS Badue, AF de Souza, ...

Proceedings of the 31st International Conference on Computational …, 2025

Depression and Anxiety Screening for Pregnant Women via Free Conversational Speech in Naturalistic Condition

RT Sousa, GDM Silva, PLL Pinto, J Backes, AS Mota, TM Paixão, ...

IEEE Access, 2025

Blast furnace control by hierarchical similarity search in historical data

LL Amorim, F Mutz, TM Paixao, V Rampinelli, AF De Souza, C Badue, ...

Engineering Applications of Artificial Intelligence 141, 109779, 2025

AI-Driven Early Mental Health Screening: Analyzing Selﬁes of Pregnant Women

GA Basílio, TB Pereira, AL Koerich, H Tavares, L Dias, MGS Teixeira, ...

18th International Joint Conference on Biomedical Engineering Systems and …, 2025

Proper Body Landmark Subset Enables More Accurate and 5X Faster Recognition of Isolated Signs in LIBRAS

DLV dos Santos, TB Pereira, CEGR Alves, RJMG Tello, FA Boldt, ...

arXiv preprint arXiv:2510.24887, 2025

RagPharma: A RAG-Based Chatbot for Medicine Leaflets with a Dual-Dataset Evaluation Framework

LC Navarro, F Mutz, TM Paixão, GG Zanetti, C Badue, AF De Souza, ...

Journal of the Brazilian Computer Society 31 (1), 1137-1149, 2025

Driver Drowsiness Detection: Comparative Analysis of BiLSTM and CNN+ BiLSTM Architectures

LTL de Souza, TM Paixao, RJMG Tello

Escola Regional de Informática do Espírito Santo (ERI-ES), 61-69, 2025

Desenvolvimento e Avaliaçao de um Sistema de Escrita e Desenho no Ar com Caneta Eletrônica e VLMs

LTL de Souza, RAD Caldeira, SDC Leal, MCP de Souza, TM Paixao, ...

Escola Regional de Informática do Espírito Santo (ERI-ES), 100-109, 2025

Pt-HotpotQA: Evaluating Multi-Hop Question Answering on Original and Portuguese-translated Datasets Using LLMs

SS Mucciaccia, TM Paixão, F Mutz, AF De Souza, CS Badue, ...

Journal of the Brazilian Computer Society 31 (1), 872-884, 2025

A machine learning approach for intra-and inter-cast hot metal temperature forecasting

TM Paixão, SS Mucciaccia, LC Navarro, F Mutz, V Rampinelli, C Badue, ...

Computers & Chemical Engineering 201, 109210, 2025

Pig Detection Using Computer Vision Models Trained on Synthetic Datasets

AV Martins, TM Paixao, FA Boldt, IC Condotta

Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), 915-926, 2025

Assessing the Effectiveness of Transfer Learning in Chest X-Ray Analysis With the BRAX Dataset

ED Silva, TB Pereira, CE Brandão, FDA Boldt, TM Paixão

IEEE Access, 2025

Previsão de demanda de curto prazo usando aprendizado de máquina com dados por telemetria: Um estudo de caso no Brasil

MR de Souza, DP Silva, TM Paixao

Seminário Integrado de Software e Hardware (SEMISH), 345-356, 2025

Enhancing Brazilian Sign Language Recognition through Skeleton Image Representation

CEGR Alves, FDA Boldt, TM Paixão

2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 1-6, 2024

Reconhecimento de Texto para Sistemas Air Writing: Um Estudo Experimental

CES Barbosa, TB Pereira, IM do Carmo, RJMG Tello, FA Boldt, TM Paixao

Escola Regional de Informática do Espírito Santo (ERI-ES), 21-30, 2024

Cross-domain object detection using unsupervised image translation

VF Arruda, RF Berriel, TM Paixão, C Badue, AF De Souza, N Sebe, ...

Expert Systems with Applications 192, 116334, 2022

Temperature prediction in blast furnaces: a machine learning comparative study

LC Navarro, LL Amorim, R Berriel, TM Paixão, V Rampinelli, LA Wasem, ...

2022 35th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) 1 …, 2022

Deep traffic sign detection and recognition without target domain real images

L Tabelini, R Berriel, TM Paixão, AF De Souza, C Badue, N Sebe, ...

Machine Vision and Applications 33 (3), 50, 2022

A human-in-the-loop recommendation-based framework for reconstruction of mechanically shredded documents

TM Paixão, RF Berriel, MCS Boeres, AL Koerich, C Badue, AF De Souza, ...

Pattern Recognition Letters 164, 1-8, 2022

Self-driving cars: A survey

C Badue, R Guidolini, RV Carneiro, P Azevedo, VB Cardoso, A Forechi, ...

Expert systems with applications 165, 113816, 2021

Keep your eyes on the lane: Real-time attention-guided lane detection

L Tabelini, R Berriel, TM Paixao, C Badue, AF De Souza, ...

Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021

Polylanenet: Lane estimation via deep polynomial regression

L Tabelini, R Berriel, TM Paixao, C Badue, AF De Souza, ...

2020 25th international conference on pattern recognition (ICPR), 6150-6156, 2021

Deep learning-based type identification of volumetric MRI sequences

JPV de Mello, TM Paixão, R Berriel, M Reyes, C Badue, AF De Souza, ...

2020 25th International Conference on Pattern Recognition (ICPR), 1-8, 2021

Deep traffic light detection by overlaying synthetic context on arbitrary natural images

JPV de Mello, L Tabelini, RF Berriel, TM Paixao, AF De Souza, C Badue, ...

Computers & Graphics 94, 76-86, 2021

A machine learning-based system for financial fraud detection

JPA Andrade, LS Paulucio, TM Paixao, RF Berriel, TCJ Carneiro, ...

Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), 165-176, 2021

Sisfrutos Papaya: A Dataset for Detection and Classification of Diseases in Papaya

JL de Moraes, J de Oliveira Neto, JR Correia-Silva, TM Paixão, C Badue, ...

International Conference on Artificial Neural Networks, 28-39, 2021

Self-supervised deep reconstruction of mixed strip-shredded text documents

TM Paixão, RF Berriel, MCS Boeres, AL Koerich, C Badue, AF De Souza, ...

Pattern Recognition 107, 107535, 2020

Fast (er) reconstruction of shredded text documents via self-supervised deep asymmetric metric learning

TM Paixao, RF Berriel, M Boeres, AL Koerich, C Badue, AFD Souza, ...

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020

Product categorization by title using deep neural networks as feature extractor

LS Paulucio, TM Paixão, RF Berriel, AF De Souza, C Badue, ...

2020 International joint conference on neural networks (IJCNN), 1-7, 2020

Cross-domain car detection using unsupervised image-to-image translation: From day to night

VF Arruda, TM Paixao, RF Berriel, AF De Souza, C Badue, N Sebe, ...

2019 International joint conference on neural networks (IJCNN), 1-8, 2019

Traffic light recognition using deep learning and prior maps for autonomous cars

LC Possatti, R Guidolini, VB Cardoso, RF Berriel, TM Paixão, C Badue, ...

2019 international joint conference on neural networks (IJCNN), 1-8, 2019

Handling pedestrians in self-driving cars using image tracking and alternative path generation with Frenét frames

R Sarcinelli, R Guidolini, VB Cardoso, TM Paixao, RF Berriel, P Azevedo, ...

Computers & Graphics 84, 173-184, 2019

Effortless deep training for traffic sign detection using templates and arbitrary natural images

LT Torres, TM Paixão, RF Berriel, AF De Souza, C Badue, N Sebe, ...

2019 international joint conference on neural networks (IJCNN), 1-7, 2019

Relevant traffic light localization via deep regression

R de Freitas, T Paixão, R Berriel, A De Souza, C Badue, T Oliveira-Santos

Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), 460-471, 2019

Exploring character shapes for unsupervised reconstruction of strip-shredded text documents

TM Paixão, MCS Boeres, COA Freitas, T Oliveira-Santos

IEEE Transactions on Information Forensics and Security 14 (7), 1744-1754, 2018

A deep learning-based compatibility score for reconstruction of strip-shredded text documents

TM Paixao, RF Berriel, MCS Boeres, C Badue, AF De Souza, ...

2018 31St SIBGRAPI conference on graphics, patterns and images (SIBGRAPI), 87-94, 2018

Texture classification of sea turtle shell based on color features: Color histograms and chromaticity moments

WR da Paixao, TM Paixao, MCB da Costa, JO Andrade, FG Pereira, ...

International Journal of Artificial Intelligence & Applications 9 (2), 55-67, 2018

Controlling First-Person Character Movement: A Low-Cost Camera-based Tracking Alternative for Virtual Reality

RF Berriel, TM Paixao, I Nicchio, T Oliveira-Santos

2018 17th Brazilian Symposium on Computer Games and Digital Entertainment …, 2018

A backmapping approach for graph-based object tracking

TM Paixão, ABV Graciano, R Hirata, RM Cesar

2008 XXI Brazilian Symposium on Computer Graphics and Image Processing, 45-52, 2008

Contact

Let's Connect

Postgraduate Program in Applied Computing (PPComp)

Av. dos Sabiás, 330, Morada de Laranjeiras, Serra, ES, 29166-630, Brazil.

Email Address

thiago.paixao@ifes.edu.br

paixao@gmail.com