Optical Flow Upsamplers Ignore Details: Neighborhood Attention Transformers for Convex Upsampling
A.S. Gielisse. (2023). Master Thesis. TU Delft Repository.
CV
Welcome to my CV page. Here, you will find a comprehensive overview of my academic and professional achievements, as well as my skills and qualifications in the field of computer science.
Education
- BSc in Computer Science, Delft University of Technology, Intelligent Data Analysis Track, 2020
- MSc in Computer Science, Delft University of Technology, Artifial Intelligence Track, 2023 (thesis grade 9.5 / 10)
- PhD in Computer Science, Delft University of Technology, Artificial Intelligence, 2023 - current (ongoing)
Teaching
As a result of pursuing an educational minor during my Bachelor’s degree, I am a certified second degree high school mathematics teacher.
I am head TA for the CS4240 Deep Learning course edition 2023 - 2024.
[May 21st 2024] I gave lecture on Vision Transformers as part of TU Delft Course CS4245 Seminar Computer Vision by Deep Learning.
Currently supervising MSc students
- Paul Frolke: Diffusion techniques for Optical Flow
- Pascal Benschop: When is depth useful for image segmentation?
- Joost Luijmes: Processing Local Implicit Neural Representations
- Thomas Streefkerk: Optical Flow Detail Imbalance
- (soon) Byran He: Implicit CNN’s
Publications
Color Equivariant Convolutional Networks
arXiv:2310.19368 Attila Lengyel, Ombretta Strafforello, Robert-Jan Bruintjes, Alexander Gielisse, Jan van Gemert