Denis Miller

“Image-service platform”

Company-wide solution of image similarity search implementing deep-learning analysis techniques, including:

  • Batch analysis and feature extraction of a billion-scaled image database
  • Building search index and search for similar images
    • Fast approximate search in billion-scaled index in 20 ms
  • Object detection
  • Face recognition
  • Attribute extraction
  • Pattern extraction for fashion items
  • Detection of
    • Frame presence
    • Background clearance
    • Text presence

Achievements

  • Architect technology solutions and software of platform.
  • Automation of indexing images, training models, updating indexes using Hadoop and Spark on top of Mesos. 
  • Architect, develop and deploy:
    • highly-scalable micro-service based architecture of search component.
    • fully-automated index building  including incremental injections.
    • similarity-search project for billion-scale index
    • visual features extractor for online and batch processes
    • API
    • in-house demo website
  • Built and led engineering team
  • 200x increased performance of image-similarity searcher by implementing fast LOPQ search
  • Viber bot to search images similar to captured from smartphone camera
  • CI/CD always
Posted in ProjectLeave a Comment on “Image-service platform”

Machine-translation powered Viber chats

PoC of using machine translations in Viber conversations.

Auto-translated chat-rooms powered by in-house translate engine with support of multilingual and multi-directional translations.

Achievements

  • Implemented PoC of translation in collaboration with Viber
  • Implemented virtual chat-rooms. Anyone, knowing chatroom password can join group conversation using his native language. Another members receive messages translated to their ones.
Posted in ProjectLeave a Comment on Machine-translation powered Viber chats

“Category prediction system” 

Automatic classification tool for predicting the correct category for a given product title and description. Under the hood is a combination of two different neural models – deep belief networks and deep autoencoders.

High scalable to categorize a large e-commerce dataset consisting of 200 millions of products and a 5-level taxonomy tree containing 28K categories.

Had a relative speech at NVidia’s GTC 2017:

Large-scale product categorization with deep models in Rakuten

Posted in ProjectLeave a Comment on “Category prediction system” 

“Beriev”

ERP- and Manufacturing-level solution automating engineering, manufacturing and repairment lifecycle of Beriev Aircraft company.

Achievements

  • Led the development team of Mobile troubleshooting system.
  • Secure Android application for helping troubleshooting of aircraft to build defect list, repair scope and schedule
  • Secure application working as intermediary between Android app and Beriev software ecosystem.
Posted in ProjectLeave a Comment on “Beriev”

GitHub publication of “IdealAudio” application

Powerful audio player for online and local music and audio-books.

Available to search media, download, set as ringtone, sort by albums, authors, folder. Has a powerful 10-band handy equalizer, great sound quality, audio cleanliness and very smooth interface. Playing the folder structure, artist or album, creating playlists.

Published to GitHub

Posted in Open-source projectLeave a Comment on GitHub publication of “IdealAudio” application

“LiveCity”

SaaS solution for housing and communal services automation.

Achievements

  • Led the team, developed all “Personal account”-relative services and applications of “LiveCity” ecosystem
  • Architected and developed integration unit with https://dom.gosuslugi.ru/ according to Russian Federal Law #209 using secure connection with signing and validation via GOST R 34.11-94 with GOST R 34.10-2001, according to Russian national standard
  • “Dispatching of meter readings” module
  • “Personal account for tenants” RESTful API, native iOS and Android applications
    (now decommissioned) https://play.google.com/store/apps/details?id=ru.malahitsoft.tenant, but available at https://apkpure.com/a/ru.malahitsoft.tenant
  • Development of front-end using HTML5, CSS3, Javascript, JQuery, AngularJS, Kendo UI
    and back-end using C#, ASP.NET MVC, Entity Framework of “LiveCity” ecosystem
Posted in ProjectLeave a Comment on “LiveCity”

“Zaycev.net”

zaycev.net is one of most popular music portals in Russia and former USSR countries.

Achievements

  • Led the development team
  • Refactored, re-supported, re-developed official Android application of zaycev.net music portal. During my support Google Play Store rank of application had increased from 4.5 to 4.8, number of downloads increased to 8 millions.
  • Authentication mechanism for Android and iOS clients
  • Zaycev Browser, a unique iOS app that combines web-surfing and music searching through page visits and official iOS app of zaycev.net allowing to listen and download music
  • Official iOS application for zaycev,net
  • Official Windows Phone application for zaycev.net
  • Official Tizen application for zaycev.net that was available at Tizen Store at the moment of it’s opening.

Continue reading ““Zaycev.net””

Posted in ProjectLeave a Comment on “Zaycev.net”