Andrey Sheka

Andrey Sheka

PhD (Cand. Phys-Math. Sc.)

About

12
Publications
975
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
16
Citations
Citations since 2017
12 Research Items
16 Citations
2017201820192020202120222023012345
2017201820192020202120222023012345
2017201820192020202120222023012345
2017201820192020202120222023012345

Publications

Publications (12)
Preprint
Full-text available
This paper proposes a method for head pose estimation from a single image. The head position estimation is carried out using a neural network (NN) obtained in two stages. At the first stage, we trained the base NN, which has one regression head and 4 regression via classification (RvC) heads. We built the offsets ensemble using small offsets of fac...
Conference Paper
Using a reduced set of facial keypoints improves the accuracy of calculating the angles of rotation of the head. In this paper, we propose methods for evaluating the accuracy of calculating angles and an algorithm for selecting a subset of facial keypoints. This approach has improved the accuracy of angle calculation by more than 50%.
Conference Paper
This paper compares the quality of segmentation of echocardiographic images of the left ventricle of the heart using 5 architectures and 38 pre-trained encoders. As part of the study, we trained 1140 neural networks. On the test dataset, the accuracy was 93.18% according to the Dice metric, which is more than our previous result at 92.78%. On cross...
Article
The precedence constrained traveling salesman (TSP-PC), also known as sequential ordering problem (SOP), consists of finding an optimal tour that satisfies the namesake constraints. Mixed integer-linear programming works well with the ‘lightly constrained’ TSP-PCs, close to asymmetric TSP, as well as the with the ‘heavily constrained’ (Gouveia, Rut...
Experiment Findings
Full-text available
SOPLIB06 instances, except for those ending in “.1”, turned out to be quite highly constrained. We were able to solve *all* of these through Dynamic Programming, with memory usage barely exceeding 2GB and in at most 11 seconds (on 16 OpenMP threads).
Preprint
Full-text available
The precedence constrained traveling salesman (TSP-PC), or sequential ordering problem (SOP), consists of finding an optimal TSP tour that satisfies the namesake constraints. Mixed integer-linear programming works well with the "lightly constrained" TSP-PCs, close to asymmet-ric TSP, as well as the "heavily constrained" TSP-PCs (Gouveia, Ruth-mair,...

Network

Cited By