|
I am a second year Ph.D. student in the GRASP laboratory at the University of Pennsylvania, where I work on deep learning and computer vision with Kostas Daniilidis. Previously, I received my bachelor's degree from Czech Technical University in Prague, where I also worked as an undergraduate researcher advised by Tomas Pajdla. For this research, I've also spent two summers at INRIA and TiTech, with Josef Sivic and Akihiko Torii respectively. My name is best pronounced as "Oleg". I also prefer being called that in less formal writing. Google Scholar / GitHub / Email / CV / LinkedIn |
|
|
My general interest is in creating neural network models that advance our computational understanding of cognition, which is broad and encompasses artificial intelligence, machine perception, and cognitive robotics. I am specifically interested in exploring how we can reproduce behavioural, cognitive and neuroscientific phenomena from humans in neural networks. Recently, I've been working on making machines perceive motion and intuitive physics in a way that is closer to human understanding. I am also interested in meta-learning and recurrent visual attention. During my bachelor's, I worked on camera geometry for structure from motion. Check out this and my other fun projects on my GitHub page. |
 
|
The method learns the action space of a robot from pure video data. This can be used e.g. to transplant a trajectory of actions from one video into another. Hover the mouse (or tap the screen) here to see the video. |
 
|
The model predicts future video frames by learning to represent the present state of a system together with a high-level transformation that is used to produce its future state. Hover the mouse (or tap the screen) here to see the video. |
|
|
|
 
|
MSE loss and its variants are commonly used for training and evaluation of future prediction. But is this the right thing to do? Hover the mouse (or tap the screen) here to see the video. |
|
|