My hometown Recife, Pernambuco, Brazil.


Oct/2021 - One paper accepted at NeurIPS21.
Mar/2021 - One paper accepted at CVPR21.
Jan/2021 - Two papers accepted at ISBI21.
Jan/2021 - Our DeepCSR paper received the best paper award (algorithm track) in the WACV21.
Aug/2020 - One paper each accepted at SASHIMI20 (MICCAI20 workshop) and WACV21.
Apr/2020 - One paper accepted to CVPR 2020 workshop on Compositionality in Computer Vision.
May/2019 - Stating a new job as postdoctoral research fellow at CSIRO.
Sep/2018 - We have our work on visual permutation learning accepted to PAMI.
Jun/2018 - Third-place in the WebVision challenge on CVPR 2018. See the Code and slides of my presentation.
Jan/2018 - One paper accepted on WACV18.
Mar/2017 - One paper accepted on CVPR17.
Mar/2017 - Workshop on introduction to CNNs using Tensorflow and Keras. Code and slides available.

Bio & Interests

I am a postdoctoral research fellow at CSIRO, Australia. I am currently working on brain image segmentation collaborating with Dr Olivier Salvado, Dr Jurgen Fripp, Dr Sam Burnham, and Dr Pierrick Bourgeat. Previously, I was a PhD. candidate in Computer Science at the Australian National University (ANU), under the supervision of PhD. Basura Fernando, PhD. Anoop Cherian and Prof. Stephen Gould. I was also associated with the Australian Centre for Robotic Vision (ACRV).

Before joining ANU, I graduated from University of Pernambuco (UPE), Brazil, with a Bachelor of Computer Engineering in August 2014. In 2013, i received a “Science Without Border” Scholarship from CNPQ, Brazil to study as an exchange student in the B.Sc. Computer Science at the Australian National University (ANU), Australia.

I have a broad interest in Computer Vision, Pattern Recognition, Machine Learning, and its applications. While I spent most of my PhD. working on problems related to visual recognition with minimal human supervision, I’m currently working on brain image segmentation. My goal is to design and build systems that can efficiently extract meaningful interpretations from visual data.