Francisco Caetano

PhD Candidate in Generative Modelling

f.t.de.espirito.santo.e.caetano@tue.nl

Logo
Francisco Caetano

About Me

Making stuff out of noise.

Contact: f.t.de.espirito.santo.e.caetano@tue.nl.

Projects

GenerativeZoo: A Unified Repository of Generative Models for Computer Vision

Francisco Caetano, Christiaan Viviers, Peter H.N. de With, Fons van der Sommen

GitHub Repository

Publications

AdverX-Ray: Ensuring X-Ray Integrity Through Frequency-Sensitive Adversarial VAEs

Francisco Caetano, C. Viviers, L. Filatova, P.H.N. de With, F. van der Sommen

SPIE Medical Imaging 2025

Runner-up 2025 Robert F. Wagner All-Conference Best Student Paper Award

Unveiling the Performance of Video Anomaly Detection Models—a Benchmark-based Review

Francisco Caetano, Pedro Carvalho, Jaime Cardoso

Intelligent Systems with Applications

Visual Data Processing for Anomaly Detection

Francisco Caetano

Master Thesis

Deep Anomaly Detection for In-Vehicle Monitoring—An Application-Oriented Review

Francisco Caetano, Pedro Carvalho, Jaime Cardoso

Applied Sciences (MDPI)

Experience

Eindhoven University of Technology

PhD Candidate
Eindhoven University of Technology

  • Generative artificial intelligence for tailored synthetic image generation
  • Supervision of dr.ir. Fons van der Sommen (Associate Professor at TU/e)
Fraunhofer Portugal AICOS

Computer Vision Researcher
Fraunhofer Portugal AICOS

  • Anomaly Detection for In-Line Visual Inspection
Faculty of Engineering, University of Porto

MSc Electrical Engineering
Faculty of Engineering, University of Porto

  • Graduated with GPA of 18/20
  • Published two journal articles during the Master Thesis
INESC Technology and Science

Research Assistant
INESC TEC - CTM

  • Recognition of human activity with occlusion-handling
  • Real-time trajectory prediction of surrounding vehicles for risk estimation.
Faculty of Engineering, University of Porto

BSc Electrical Engineering
Faculty of Engineering, University of Porto

  • Graduated with GPA of 18/20
This website is based on the one created by Tim Schoonbeek, available here