EYEgor Yarko

Egor Yarko

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Egor Yarko has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Comparative Analysis of Libraries for Human Pose Detection in Mobile Device Environments

    by E. I. Yarko

    Human pose estimation (HPE) is among the most relevant topics in computer vision research. This technology can be applied in various fields, such as video

  • Open Access

    Comparative Analysis of Libraries for Human Pose Detection in Mobile Device Environments

    by Egor Igorevich Yarko

    Human Pose Estimation (HPE) has become one of the most relevant topics in computer vision research. This technology can be applied in various fields such as video surveillance, medical care, and sports motion analysis. Due to the increasing demand for HPE, many libraries for this technology have been developed in the last 20 years. Since 2017, many HPE algorithms based on skeletal model have been published and packaged into libraries for easy use by researchers. These libraries are important for researchers who want to integrate them into real-world applications for video surveillance, medical care, and sports motion analysis. This paper investigates the strengths and weaknesses of four popular HPE advanced human pose recognition libraries that can run on mobile devices: Lightweight OpenPose, PoseNet, MoveNet, and Blase Pose.

  • Open Access

    Crystal Nucleation and Growth in Cross-Linked Poly(ε-caprolactone) (PCL)

    by Timur Mukhametzyanov, Jürn W.P. Schmelzer, Egor Yarko, Albert Abdullin, Marat Ziganshin, Igor Sedov, Christoph Schick

    The crystal nucleation and overall crystallization kinetics of cross-linked poly(ε-caprolactone) was studied experimentally by fast scanning calorimetry in a wide temperature range. With an increasing degree of cross-linking, both the nucleation and crystallization half-times increase. Concurrently, the glass transition range shifts to higher temperatures. In contrast, the temperatures of the maximum nucleation and the overall crystallization rates remain the same, independent of the degree of cross-linking. The cold crystallization peak temperature generally increases as a function of heating rate, reaching an asymptotic value near the temperature of the maximum growth rate. A theoretical interpretation of these results is given in terms of classical nucleation theory. In addition, it is shown that the average distance between the nearest cross-links is smaller than the estimated lamellae thickness, which indicates the inclusion of cross-links in the crystalline phase of the polymer.


  • Open Access

    Influence of the Cross-Link Density on the Rate of Crystallization of Poly(ε-Caprolactone)

    by Igor Sedov, Timur Magsumov, Albert Abdullin, Egor Yarko, Timur Mukhametzyanov, Alexander Klimovitsky, Christoph Schick

    Cross-linked poly(ε-caprolactone) (PCL) is a smart biocompatible polymer exhibiting two-way shape memory effect. PCL samples with different cross-link density were synthesized by heating the polymer with various amounts of radical initiator benzoyl peroxide (BPO). Non-isothermal crystallization kinetics was characterized by means of conventional differential scanning calorimetry (DSC) and fast scanning calorimetry (FSC). The latter technique was used to obtain the dependence of the degree of crystallinity on the preceding cooling rate by following the enthalpies of melting for each sample. It is shown that the cooling rate required to keep the cooled sample amorphous decreases with increasing cross-link density, i.e., crystallization process slows down monotonically. Covalent bonds between polymer chains impede the crystallization process. Consequently, FSC can be used as a rather quick and low sample consuming method to estimate the degree of cross-linking of PCL samples.