I am currently a Ph.D. Candidate in Computer Science in the Computer Science Department at Universidade Federal de Minas Gerais (UFMG), Brazil, and I had been a Visiting Researcher in the School of Computing and Communications at Lancaster University (LU), United Kingdom from September 2019 to March 2020. I am under the supervision of Erickson R. Nascimento and Leandro S. Marcolino. I received my MSc degree in Computer Science from Universidade Federal de Minas Gerais (UFMG) in March of 2017 and my BSc degree in Computer Science from Pontifícia Universidade Católica de Minas Gerais (PUC-Minas) in December of 2013.
In my research, I address the problem of semantic extraction in temporally untrimmed videos, especially those of long duration, such as egocentric videos. To evaluate our outcomes, I explore the task of semantic video fast-forwarding via adaptive frame selection, which consists of producing videos that are both pleasant to watch and informative. In the current stage, I am investigating and proposing novel multimodal representation learning approaches. More specifically, I explore the semantic connections between language and vision by using a set of sentences (e.g., textual posts in Social Networks, steps of a certain task) to personalize the creation of the shorter/accelerated version of the input video.
PhD in Computer Science, Current
Universidade Federal de Minas Gerais (UFMG)
MSc in Computer Science, 2017
Universidade Federal de Minas Gerais (UFMG)
BSc in Computer Science, 2013
Pontifícia Universidade Católica de Minas Gerais (PUC-Minas)
We’ve got our journal paper accepted to the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)!
Our paper is titled “Text-driven video acceleration: A weakly-supervised reinforcement learning method”. For more details about the paper, please visit the Publications Section.
Our conference paper “Musical Hyperlapse: A Multimodal Approach to Accelerate First-Person Videos” was awarded the Best paper on Pattern Recognition and Related Fields in the 34th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)!
For more details about the paper, please visit the Publications Section.
I’ve been selected as one of the 2021-2022 Microsoft Research PhD Fellows!!
More details about the fellowship in the Awards Section.
Preprint PDF Code Dataset Project Poster Video Conference Website
Our paper titled “Musical Hyperlapse: A Multimodal Approach to Accelerate First-Person Videos” has been awarded the best Pattern Recognition and Related Fields paper in the SIBGRAPI 2021 - 34th Conference on Graphics, Patterns and Images.
Details about the paper can be found in the Publications Section and in the project website.
I’ve been selected as one of the 2021-2022 Microsoft Research PhD Fellows!!
This program is for PhD students at universities globally pursuing research aligned to the Microsoft Research areas of focus. Students were selected by region, and I am among those selected in Latin America.
Details about the process I followed in order to be awarded can be found in this link.
Submitted Project: “Text-driven Hyperlapse: A Weakly-Supervised Video Acceleration Approach Using Vision-Language Modeling”
My M.Sc. Dissertation titled “Semantic Hyperlapse for Egocentric Videos” has been awarded the best Computer Vision/Image Processing/Pattern Recognition M.Sc. Dissertation in the SIBGRAPI 2017 - 30th Conference on Graphics, Patterns and Images (Workshop of Theses and Dissertations).
Details about the paper can be found in the Publications Section. You can get the full dissertation through this download icon:
My presentation has been has been awarded as the Best Presentation of Master’s Work Dissertation at Week of Graduate Seminars held by the Departamento de Ciência da Computação (DCC-UFMG).
My M.Sc. Dissertation is titled “Semantic Hyperlapse for Egocentric Videos” and it can be downloaded here.
Click here for more info about the award (in Portuguese).