My name is Michal Neoral and I am a researcher at the Visual Recognition Group (VRG) at the Faculty of Electrical Engineering, Czech Technical University in Prague. I am currently a PhD candidate, supervised by prof. Jiří Matas and Dr. Jan Šochman. My dissertation, which is now under review, focuses on dense pixel-level tracking in video, with emphasis on optical flow estimation, occlusion handling, and motion segmentation. My broader research interests lie in long-term correspondence estimation, where I aim to develop robust methods that maintain temporal consistency across extended video sequences. Recently, I have also been working on efficient detection and classification techniques for fast processing of large-scale data, as part of the AISEE project. During my PhD, I had the opportunity to collaborate with Toyota Motor Europe, and I would like to sincerely thank them for their generous support throughout my doctoral studies.

Education

• Ph.D. candidate
  2018 -- 2025 (ongoing)
  Czech Technical University in Prague, Prague, Czech Republic
  Faculty of Electrical Engineering
  field of Study: Informatics / Artificial Intelligence and Biocybernetics
  dissertation topic: Dense Motion Estimation in a Monocular Video
  supervisor: prof. Ing. Jiří Matas, Ph.D.
  co-supervisor: Mgr. Jan Šochman, Ph.D.
  


• Master's degree in engineering -- Ing. (MSc equivalent)
  2014 -- 2017
  Czech Technical University in Prague, Prague, Czech Republic
  Faculty of Electrical Engineering
  program: Open Informatics
  specialization: Computer Vision and Image Processing
  thesis topic: Object Scene Flow in Video Sequences
  supervisor: Mgr. Jan Šochman, Ph.D.
  


• Bachelor's degree in engineering -- Bc. (BSc equivalent)
  2011 -- 2014
  Czech Technical University in Prague, Prague, Czech Republic
  Faculty of Electrical Engineering
  program: Cybernetics and Robotics
  specialization: Robotics
  thesis topic: Extraction of Features from Moving Garment
  supervisor: Ing. Pavel Krsek, Ph.D.