We are looking for 2 students / PhD students to work on video generation using deep learning in NCN SONATA grant.
Project description: Generative models using deep learning have witnessed increasing attention in recent years. In this project. we focus on video generation and 3 research topics. Firstly, we focus on the highly intricate problem of video generation without prior knowledge w.r.t. either appearance or motion, and on learning a disentangled representation of the video generative factors appearance and motion, allowing for manipulation of both. We want to improve spatial resolution and temporal length of generated content and synthesise high-quality and high-resolution videos with limited training data. Secondly, we focus on conditional video generation to allow for manipulation of generated video content. Finally, we focus on probabilistic video generation, which is particularly important for video forecasting.
More information: https://mimuw.edu.pl/~bilinski/video_generation/stipend2.html .
This is ongoing project at University of Warsaw, Faculty of Mathematics, Informatics, and Mechanics.
Score of work:
- Research and development of novel computer vision and machine learning algorithms.
- Performing scientific experiments. Performing analysis of experiments and results.
- Writing timely reports on the research and publishing these as papers.
- Performing occasional demonstrations.
- Contributing documented software to the group library.
Required professional qualifications:
- Status of a student or doctoral student in Poland.
- Good knowledge about the state-of-the-art in computer vision and machine learning.
- Good programming skills: Python, Numpy and PyTorch/ TensorFlow/ Keras/ Caffe/ similar deep learning framework.
- Good communication skills, including the ability to write for publication, present research proposals and results.
- Ability to work independently.
- Fluent English.