Academic achievements of the MSci in Data Science alumni and students in 2019
636
In 2019, the students and alumni of the MSci in Data Science continued to actively publish their research. Most of those papers were the results of the diploma projects.
- Orest Kupyn (the graduation year 2018), Tetiana Martyniuk (the graduation year 2019), Junru Wu, Zhangyang Wang. DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better. arXiv preprint. Presented at the top-tier international conference on computer vision – ICCV 2019. The paper includes the results of the diploma project by Tetiana Martyniuk.
- Irynei Baran (the graduation year 2019), Orest Kupyn (the graduation year 2019), A. Kravchenko. Safe Augmentation: Learning Task-Specific Transformations from Data. arXiv preprint. The paper is accepted for the conference in computer vision WACV 2020 and is based on the research provided by Irynei Baran during his diploma project.
- Orest Kupyn (the graduation year 2018), D. Pranchuk. Fast and Efficient Model for Real-Time Tiger Detection In The Wild. arXiv preprint, 2019.
- Hanna Pylieva (the graduation year 2019), Artem Chernodub, Natalia Grabar, Thierry Hamon. Generalizability of Readability Models for Medical Terms. The paper is presented at the conference MEDINFO 2019 and published at Studies in Health Technology and Informatics. This paper as the following one is the result of Hanna’s diploma project research.
- Hanna Pylieva (the graduation year 2019), Artem Chernodub, Natalia Grabar, Thierry Hamon. RNN Embeddings for Identifying Difficult to Understand Medical Words. The paper is presented at the SIGBioMed workshop, 2019.
- J. Pritts, Z. Kukelova, V. Larsson, Yaroslava Lochman (the graduation year 2020), O. Chum. Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales. arXiv preprint. The paper is accepted for IJCV, 2019.
- Oleh Lukianykhin (the graduation year 2020), T. Bogodorova. ModelicaGym: Applying Reinforcement Learning to Modelica Models. EOOLT 2019. arXiv preprint. The paper was presented at the EOOLT2019 conference, Berlin.