19 Янв, 2016

Presentation on Video Recognition (animations in the folder)


Abstract. Video recognition is an increasingly popular research area with applications in security, human behavior analysis, education, entertainment and different business tasks. Because of the complexity of most of the video data, this area needs new scientific methods before we can benefit from it in practice. In this presentation, we will consider the most advanced methods including hand-crafted features based on optical flow and learned features like convolutional neural networks. Some of the previous results were reproduced and improved in my works. Finally, a new method based on our recent developments in the image recognition area along with its results will be presented and discussed.

22 Сен, 2014

В папке 2014/DigitRecognition ожидается появление материалов по распознаванию рукописных цифр, в том числе исходных кодов MATLAB, с помощью которых была получена ошибка классификации 0.60% на базе MNIST.

См. файл classifyDigits.m.

See folder 2014/DigitRecognition in which there is code (classifyDigits.m) and .mat files to run a simple digits classification algorithm with a 0.60% error rate on the MNIST set.

16 Сен, 2013
16 Сен, 2013
CVPR 2014, Submission Deadline: November 1, 2013 http://www.pamitc.org/cvpr14/ ECCV 2014, Submission Deadline: March 7, 2014 http://eccv2014.org/
08 Мар, 2013
Calendar of Computer Image Analysis, Computer Vision Conferences: http://iris.usc.edu/information/Iris-Conferences.html Top conferences in computer vision: http://academic.research.microsoft.com/RankList?entitytype=3&topDomainID=2&subDomainID=11
08 Мар, 2013
9th International Conference on Computer Vision Systems St. Petersburg, Russia http://workshops.acin.tuwien.ac.at/ICVS/index.html