Human gait recognition in video (2016-2018)

During this project we have developed CNN-based gait recognition methods, reaching state-of-the-art on TUM GAID and OU-ISIR datasets.

Medical image analysis

Development of efficient and convenient algorithms for automatic analysis of magnetic resonance images (MRI) and computed tomography images (CT). We work with brain and cardiac images.

MSU Video Codec Comparison

MSU Codec Comparison aims to deliver high quality comparisons of video encoders to both industrial and scientific communities. Since 2003 our team publishes annual reports with codecs’ comparisons.

Old projects

Old projects of our lab.

Selected completed projects (2002-2014)

Selected projects of Graphics & Media Lab - best publications and most prominent results.

Semiautomatic Visual-Attention Modeling

We found that automatic models are significantly worse at predicting attention than even single-observer eye tracking. We propose a semiautomatic approach that requires eye tracking of only one observer and is based on time consistency of the observer’s attention.

Video Matting Benchmark

Video matting refers to a problem of accurate decomposition of given video sequence to background layer, foreground layer and transparency map.
The VideoMatting project is the first online benchmark of video matting methods. The goal of the project is to provide better understanding of current progress in the field of video matting and to aid in developing new methods.