Roman V. Shapovalov

(Роман Викторович Шаповалов)

I am currently a PhD student in the Mathematical Prediction Department and Graphics & Media Lab at Moscow State University. My research interests include (but are not limited to) machine learning, its applications to computer vision, and whiskey. My advisor is Dmitry Vetrov.

My primary field of study is recognition. Specifically, now I investigate sequential classification as an alternative to graphical models for object detection and segmentation. I am also interested (though have no particular experience) in object tracking and its applications to markerless augmented reality. I also plan (in the looong run) to develop a simple home video surveilance system (eJanitor) and a content-based music recommendation system (although recent Google's interest to industrial quality music analysis ruins my motivation). However, if you are ready for collaboration, feel free to contact me.

Selected publications

R. Shapovalov, A. Velizhev. "Cutting-Plane Training of Non-associative Markov Network for 3D Point Cloud Segmentation". IEEE International Conference on 3D Digital Imaging, Modeling, Processing, Visualisation and Transmittion (3DIMPVT 2011). Hangzhou, China. May 2011. [pdf]

R. Shapovalov, A. Velizhev, O. Barinova. "Non-associative Markov networks for 3D point cloud classification." Photogrammetric Computer Vision and Image Analysis (PCV 2010). Paris, 2010. [pdf, slides-pptx by A.Velizhev]

R. Shapovalov. "Automated object detection in laserscanning data." [In Russian] Masters Thesis, Lomonosov Moscow State University, 2010. [pdf, slides-pdf, slides-pptx]

O. Barinova, R. Shapovalov, S. Sudakov, A. Velizhev, A. Konushin. "Efficient road mapping via interactive image segmentation." 3D City Models, Road Databases and Traffic Monitoring (CMRT 2009). Paris, 2009. [pdf, slides-ppt by A.Velizhev]

Code

GML LidarK Library — the library for LIDAR data processing. Currently, only the indexing data structure is implemented. It allows performing spatial queries in 3D space. The code is C++, MATLAB wrapper is also available.

GML BOLT — the toolkit for on-line learning from imbalanced streams. It contains an on-line implementation of the Random Forest algorithm.

Non-research interests

I enjoy snowboarding, cycling, urban orienteering and editing Wikipedia. I also learn to play electric guitar. And those are only virtuous ones! ;)