I am a PhD Candidate in Computer Science at Artificial Intelligence (Recod.ai) Lab in the Institute of Computing at the University of Campinas (Unicamp) under the supervision of Professor Sandra Avila and co-supervision of Professor Esther Colombini. Also, I am a member of the Artificial Intelligence and Cognitive Architectures Hub (H.IAAC). I am interested in Natural Language Processing (NLP) and Multimodal Representation Learning. Lately, my research has been focusing on investigating low-cost strategies for training vision-language models (VLMs) for Portuguese and cultural challenges in NLP.

Interests
  • NLP
  • Multimodality
  • Cultural Challenges
  • Deep Learning
Education

  • PhD in Computer Science, Ongoing

    University of Campinas, Institute of Computing

  • BSc in Computer Science, 2021

    University of Campinas, Institute of Computing

Experience

 
 
 
 
 
PhD Candidate
University of Campinas
Mar 2022 – Present Campinas-SP, Brazil
PhD Student at Artificial Intelligence (Recod.ai) Lab.
 
 
 
 
 
Teacher Assistant of ML
University of Campinas
Aug 2023 – Dec 2023 São Paulo, Brazil
I assisted in the planning and preparation of materials for classes, in the elaboration and correction of Machine Learning projects, and in the organization and supervision of practical classes. Also, I worked on extra class assistance.
 
 
 
 
 
Deep Learning Tutor (Volunteering)
Iris Data Science UNICAMP
Mar 2022 – Dec 2023 São Paulo, Brazil
I was voluntarily a tutor in the Deep Learning course at Iris Data Science UNICAMP. Iris is a student association that aims to introduce Data Science concepts to undergraduate students who want to get to know the field. The Deep Learning course comprehends theoretical classes and practical activities so that, at the end of it, the students can understand the main components of a neural network and implement from scratch a fully connected architecture besides fine-tuning models using off-the-shelf frameworks.
 
 
 
 
 
Teacher Assistant of ML
University of Campinas
Aug 2022 – Dec 2022 São Paulo, Brazil
I assisted in the planning and preparation of materials for classes, in the elaboration and correction of Machine Learning projects, and in the organization and supervision of practical classes. Also, I worked on extra class assistance.
 
 
 
 
 
Undergraduate Research Student
University of Campinas
Feb 2019 – Jan 2022 Campinas-SP, Brazil
My undergraduate research project relies on the theme “AI for Social Good” and aims to include visually impaired people on the Internet through Machine Learning. Our main goals were to construct the first large dataset composed of images annotated with Portuguese captions and to study image captioning models. I worked with data collection, cleaning, clustering, and visualization techniques, as well as vision and language deep learning models. As a result, we proposed the #PraCegoVer dataset, the first large dataset for image captioning in Portuguese, and CIDEr-R which is a robust evaluation metric in the context of single reference captions with long sentences and high variance in length.
 
 
 
 
 
Software Developer Jr.
Dextra Digital
Nov 2017 – Mar 2018 Campinas-SP, Brazil
 
 
 
 
 
Software Developer Intern
Dextra Digital
Jan 2017 – Oct 2017 Campinas-SP, Brazil

Recent Publications

All Publications

Gabriel Oliveira, Diego A. B. Moreira, Alef Iury Ferreira, Jhessica Silva, Luiz Pereira, Pedro Bueno, Thiago Sousa, Helena Maia, Nádia Da Silva, Esther Colombini, Helio Pedrini, Sandra Avila (2023). CAPIVARA: Cost-Efficient Approach for Improving Multilingual CLIP Performance on Low-Resource Languages. In MRL @ EMNLP 2023.

PDF Cite Code DOI Models

Gabriel Oliveira, Esther Colombini, Sandra Avila (2022). #PraCegoVer: A Large Dataset for Image Captioning in Portuguese. In Data.

PDF Cite Code Dataset DOI

Gabriel Oliveira, Esther Colombini, Sandra Avila (2021). CIDEr-R: Robust Consensus-based Image Description Evaluation. In W-NUT @ EMNLP 2021.

PDF Cite Code DOI

Recent Posts

Fundamentals of Neural Networks
Inspired by the human brain, Artificial Neural Networks are powerful models that excel at recognizing patterns. Recently, thanks to advances in parallel computing, these models have been largely employed to solve many complex problems in different fields such as Computer Vision, Natural Language Processing, Robotics, Drug Discovery, etc. In this article, we are going to describe the theoretical fundamentals of Artificial Neural Networks.
Gabriel Oliveira
Jan 5, 2022 0 min read Deep Learning, Neural Networks
Fundamentals of Neural Networks
Attention to Transformer, please!
The Transformer architecture is considered a breakthrough and has been largely employed in NLP and, more recently, in Computer Vision areas. So, in this article, we are going to focus on Transformers architecture and hack it.
Gabriel Oliveira
Nov 11, 2021 0 min read Deep Learning, Transformers
Attention to Transformer, please!

Awards

Euler Award
Institute of Computing - University of Campinas Dec 2022
It acknowledges the student who has achieved the best performance, among those that completed the Computer Science course.
See certificate
Outstanding Student
Brazilian Computer Society (SBC) Dec 2021
It acknowledges the student with the best academic performance.
See certificate
Student of Great Distinction
Institute of Computing - University of Campinas Dec 2021
It acknowledges students who have achieved an overall average greater than 90%.
Scientific Merit
Dean of research of the University of Campinas Dec 2020
It acknowledges the best 20 works presented at the XXVIII Congress of Undergraduate Researchers of the University of Campinas.
See certificate
Pascal Award
Institute of Computing - University of Campinas Dec 2019
It acknowledges the student who has achieved the best performance, among those that completed between 50% and 70% of the Computer Science course.
See certificate