Profile

Cover photo
Nick Sergievskiy
Works at Elvees-Neotek
Attended МАИ
Lives in Москва
34,948 views
AboutPostsPhotosYouTube

Stream

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
Любопытно что в команде мурманска 3 человека 1:10:27
 ·  Translate
2
KuBa KuBiCH's profile photo
 
+Nick Sergievskiy вырезанную шутку на 1:03:42 вставили сюда 1:10:25
 ·  Translate
Add a comment...

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
Good sound, but I feel fear, when i see these women x_x
1
Add a comment...

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
Качественная музыка! Приятно слушать!
 ·  Translate
1
Add a comment...

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
Разве Путин что-то сделал для того чтобы считаться сильным лидером? Он вполне заурядный политик -- умеет хорошо говорить, но за ним нет никаких экономических или внешнеполитических достижений
 ·  Translate
1
Add a comment...

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
What about occlusion and deformation (rotate head 3 angles)?
1
Add a comment...
 
Intresng that best resault in Face Recognition is synchronously published Face++ (http://arxiv.org/abs/1403.2802) and facebook ( https://www.facebook.com/publications/546316888800776/ )
0.9727 ± 0.0065 vs 0.9725 ± 0.0081
Abstract: Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy-to-implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement ...
14
7
Alberto Albiol's profile photoYang Chen's profile photoNegar Hassanpour's profile photoRameswar Panda's profile photo
 
Face++ used CNN with 6M parameters.
FB used NN with 120M parameters(no weight sharing).
Both showed similar accuracy result - speaking of power of convolutions...

But mine question, anyone had a chance to look at F++ paper? How Pyramid CNN is different from ordinarily CNN? F++ just trained CNN with one convolutional layer, then another CNN with two conv layers, but output of first c-layer shared in two layered CNN, then 3 layer CNN reuse output of first 2 convolutional layers from previous CNN... With  classifiers of each CNN trained independently, is that is what going on?
Add a comment...

Nick Sergievskiy

Shared publicly  - 
1
1
Tatiana Sergievskaya's profile photo
Add a comment...

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
С ирокезом более узнаваем... Снова молодость :)
 ·  Translate
1
Add a comment...
 
Hello
I'm trying to start biohacking. What apps (Android or Web Interface) do you suggest to track my health?
1. Pressure
2. Glucose
3. Happines
4. Heart rate
5. Food (with  coffeine and alcohol)
1
Nick Sergievskiy's profile photoRyan Ostendorf's profile photoJesper Dagsberg's profile photo
7 comments
 
+Nick Sergievskiy I think the latest food sensitivity app is called Bulletproof Food Detective. I don't know if it works on Android.
Add a comment...

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
Крутая серия!
 ·  Translate
1
Add a comment...

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
Magic!
1
Add a comment...

Nick Sergievskiy

commented on a video on YouTube.
Shared publicly  - 
 
Чел в метро действительно прикольный, пару раз видел, настроение поднимается от его позитивной речи
 ·  Translate
2
Add a comment...
People
Education
  • МАИ
    2015
Basic Information
Gender
Male
Work
Occupation
programmer-analyst in Computer Vision
Skills
C++, STL, Matlab, computer vision, object detection, machine learning, textmining, deep neural network
Employment
  • Elvees-Neotek
    programmer-analyst, 2012 - present
    Projects: Car detection LicPlate recognition Face recognition
Places
Map of the places this user has livedMap of the places this user has livedMap of the places this user has lived
Currently
Москва
Links