Літня майстерня з Computer Vision, 3-7 липня
Частина 1. Statistical Decision Theory in Computer Vision, Structural Prediction and Learning
Starting toolbox for statistical recognition. Modeling with uncertainty, making decisions under uncertainty, the role of the loss function, estimating probabilistic models and making predictions with uncertainty. This classical framework is illustrated on simple computer vision examples: detection, tracking, noisy image recovery with nuisance parameters.
Probabilistic models of structured objects: from hidden Markov models to Markov Random Fields. These models are well suited for problems such as reading a license plate (sequence of digits), performing image segmentation and much more.
We consider learning of structured models. Learning conditionally independent models with maximum likelihood (image segmentation). Learning structured models by empirical risk minimization with structured support vector machine approach.
Частина 2. Буде оголошена невдовзі…
Python, Machine Learning basics, Neural Networks. It is good to be familiar with one of the Deep Learning framework.
Alexander Shekhovtsov, PhD
Researcher at Center for Machine Perception (CMP), Czech Technical University in Prague.
– 2006–2013 Ph.D., Czech Technical University in Prague, Faculty of Electrical Engineering. Thesis: “Exact and Partial Energy Minimization in Computer Vision”. Supervised by Prof. Vaclav Hlavac.
– 1998–2005 MSc., National Technical University of Ukraine KPI, Faculty of Physics and Technology, 2005, degree in applied mathematics.
– 2017–present Postdoctoral Researcher at CMP
– 2014–2016 Postdoctoral Researcher at Institute for Computer Graphics and Vision at Graz University of Technology
– 2005–Jan 2014 Researcher at CMP
– 2001–2005 Part-time engineer at International Research and Training Center for Information Technologies and Systems, Kiev, Ukraine, department of Pattern Recognition, under supervision of Schlesinger M.I
Engineer at Augmented Pixels.
– 2011–2016 Ph.D., Czech Technical University in Prague, Faculty of Electrical Engineering. Thesis: “Discriminative learning from partially annotated examples”. Supervised by Prof. Vaclav Hlavac and PhD. Vojtech Franc.
– 2004-2010 M.Sc. and B.Sc. in Applied Mathematics at the Faculty of Cybernetics, Taras Shevchenko National University of Kyiv
– 2016 – now Engineer at Augmented Pixels
– 2014 – Intern at Google
– 2011–2016 Research engineer at CMP
– 2009–2010 Part-time engineer at International Research and Training Center for Information Technologies and Systems, Kiev, Ukraine, department of Pattern Recognition, under supervision of Schlesinger M.II
Apply for the Computer Vision Workshop