Deepak Kumar
Email:
mir.em.@kkcaa3plaudrgome unscramble
I am a Software Engineer at Google. Prior to this I
worked for Microsoft on Edge browser logging for
Bing feature enhancement, at Search Technology Center India,
Hyderabad.
Before this I worked on flight booking experience on
Bing. The experience is shipped in 200 different regions and languages.
I had also interned at Microsoft in Summer 2015 working on leverageing Openstreetmap for Bing Maps after which I was offered a
full time role at Microsoft. Before all this I graduated from IIT
Kanpur in 2016 with Bachelors in Computer Science and Engineering. I did most of the projects
under Prof. Vinay Namboodiri on computer
vision. During my time here I also volunteered for NGO BloodConnect with a mission to tackle the blood shortage
in Kanpur.
|
CV |
Github |
LinkedIn |
SO
|
|
Pedestrian detection using fast R-CNN
Deepak Kumar, Mohit Singh Solanki (2016)
Advisor: Prof Vinay P Namboodiri
report |
poster |
description |
code
Finetuned ImageNet pretrained model to adapt to pedestrian detection by
changing the final CNN innerproduct layer. Used this caffe model to generate
feature vector corresponding to each bounding box. Trained a LinearSVM for final
classification. Obtianed overall precision of 88.2% on INRIA person dataset.
|
|
Background foreground frame classification
Deepak Kumar, Jay Pandya, Akhilesh Maurya, Rahul Mehra (2016)
Advisor: Prof Harish Karnick
report |
description
Implemented a real-time background-foreground classifier for the surveillance videos of IIT
Kanpur.
Used GoogLeNet pretrained model to generate feature vector for each frame and trained it on
LinearSVM.
Obtained an overall precision of 85% with a processing rate of 220 fps on GPU enabled machine.
|
|
Scalable Vocabulary tree for Image Classification
Deepak Kumar, Mohit Singh Solanki (2016)
Advisor: Prof Vinay P Namboodiri
report |
description |
code
Created a scalable vocabulary tree for object recognition on UKY dataset.
Used hierarchical k-Means clustering on SIFT features to create the tree and implemented idf
based scoring.
Evaluated the created vocabulary tree with different branch factors and different depths.
|
|
Poster Presentation: Learning to recognize Objects from Unseen Modalities
Deepak Kumar, Shishir Mathur (2015)
Advisor: Prof Vinay P Namboodiri
description |
poster |
paper
Exploited multiple sources of information for object recognition tasks when additional
modalities that are not present
in the labelled training set are available for inference.
Predicted the missing data for the labelled examples and exploited all modalities using multiple
kernel learning.
Performed hallucination to infer the missing modalities in the labelled dataset.
|
|
Automated Air Hockey
Deepak Kumar, Prashant Chawla, Shubham Patel, Nikhil Patil (2013)
Funded by Dean of Resource Planning and Generation, IIT Kanpur
video |
description
Implemented ‘Air Hockey’ game between two bots (One completely automated, other manually
controlled).
Studied the accuracy in positioning of the automated bot on approach of ball when hit by the
manual bot.
Optimized the positioning of the bot by improving algorithm for ball detection (using overhead
camera) and dynamic
calibration of the rpm of motors.
|
|
Fingerprint attendance system
Deepak Kumar, Priyaranjan, Rajat Chaudhary, Durgesh Deep (2014)
Advisor: Prof Amey Karkare
report |
description |
code
Developed a Biometric Fingerprint based attendance system with storage of 200 fingerprints at a
time.
The device could be circulated in a class and the attendance automatically marked in the
professor’s PC. Implemented
python based user-friendly GUI and MySQL based queries for easy extraction of records for each
course and individual
student.
|
|
Perl Compiler
Deepak Kumar, Nikhil Patil, Avikalp Kumar Gupta (2015)
Advisor: Prof Subhajit Roy
description |
code
Implemented an end to end compiler for Perl in python which generates machine code for x86
architecture.
Supported data types such as Integers, Strings along with operators, statements, loops and
functions (recursive).
|
|
Interpreter for Oz
Deepak Kumar, Vineet Purswani, Ayushman Singh Sisodiya (2015)
Advisor: Prof Satyadev Nandkumar
description |
code
Implemented a meta circular interpreter for a declarative sequential model for Oz.
Provided support for unification, record operations and pattern matching, over an abstract
implementation of the
single assignment store and semantic stack using easy-to-parse abstract syntax.
|
|
Course Info
Deepak Kumar, Prashant Chawla (2015)
site |
description |
code
Scraped institute’s course data of past 5 years and made it available to the students during
pre-registration time.
Added the list of students who opted for a particular course in a particular year so that one
could get to know who to
contact for a particular course’s content and structure.
Received ~5000 hits in one week.
|
Awards and Achievements
- C.S. Venkataraman Memorial Award for Rank 3 in Kerala in RMO 2011.
- Among top 30 students in Kerala selected for Indian National Mathematics Olympiad (INMO) 2011.
- Dr BR Ambedkar National Merit Award for highest marks in India in CBSE (Science Medical) among
eligible candidates (2013).
- State Rank 1 in National Science Olympiad 2009 organised by SOF.
|
MOOCs & other courses
Computer Science and Math
- Probability Theory, Statistics and Exploratory Data Analysis (Coursera Jun 2021)
- The bits and bytes of computer networking (Coursera Feb 2021)
- Introduction to Graph Theory (Coursera Jan 2021)
- Programming Languages Part C (Coursera Jan 2021)
- Programming Languages Part B (Coursera Dec 2020)
- Programming Languages Part A (Coursera Dec 2020)
- C++ 17: Beyond the basics (Pluralsight Nov 2020)
- Accessibility for web design (Linkedin Learning Oct 2020)
- Async programming in c# (Linkedin Learning Oct 2020)
- C++ Pointers (Linkedin Learning Oct 2020)
- Parallel and Concurrent programming with c++ part 1 (Linkedin Learning Oct 2020)
- Parallel and Concurrent programming with c++ part 2 (Linkedin Learning Oct 2020)
- npm and Node package manager (Linkedin Learning Sep 2020)
--- show more ---
- ASP.NET Core Internationalization Deep Dive (Pluralsight Aug 2020)
- C# Delegates, Events and Lambdas (Linkedin Learning Jun 2020)
- Azure admin essential training (Linkedin Learning Apr 2020)
- UML Mini Course (Lagunita: Stanford Online Mar 2020)
- OLAP Mini Course (Lagunita: Stanford Online Mar 2020)
- Relational Design Theory (Lagunita: Stanford Online Feb 2020)
- Getting started with Git (Pluralsight Feb 2020)
- Git: The big picture (Pluralsight Feb 2020)
- ASP.NET MVC5 Fundamentals (Pluralsight Jan 2020)
- SQL Mini Course (Lagunita: Stanford Online Nov 2019)
- ASP.NET Core 3.0: The MVC Request Life Cycle (Pluralsight Oct 2019)
- Fibonacci Numbers and the Golden Ratio (Coursera Oct 2019)
- Relational Algebra (Lagunita: Stanford Online Sep 2019)
- How Git Works (Pluralsight Jul 2019)
- Mastering Git (Pluralsight Jul 2019)
- Learning Ecmascript 6 (Linkedin Learning Feb 2019)
- Learning Webpack 1 (Linkedin Learning Feb 2019)
- Webpack for React Applications (Linkedin Learning Feb 2019)
- Learning Redux (Linkedin Learning Jan 2019)
- C# Object Oriented Programming Tips and Tricks (Linkedin Learning Dec 2018)
- Introduction to Mathematical Thinking (Coursera Dec 2018)
- Threading in C# (Linkedin Learning Jun 2018)
- Combinatorics and Probability (Coursera Dec 2017)
- Mathematical Thinking in Computer Science (Coursera Dec 2017)
- Build a Modern Computer from First Principles: From Nand to Tetris (Project-Centered Course)
(Coursera Nov 2017)
- An Intuitive Introduction to Probability (Coursera Nov 2017)
- XML Data (Lagunita: Stanford Online Oct 2017)
- JSON Data (Lagunita: Stanford Online Oct 2017)
Others (Just for knowledge)
- Understanding Medical Research (Coursera Jan 2021)
- Stanford's short course on breast feeding (Coursera Jul 2020)
- Stories of infection (Coursera June 2020)
- Photoshop: Adding style to a studio portrait (Linkedin Learning Jun 2020)
- So you think you can tango (Coursera Mar 2020)
- Fashion as Design (Coursera Mar 2020)
- Learning portrait photography (Linkedin Learning Jan 2020)
- Lightroom for faces (Linkedin Learning Jan 2020)
- Lightroom: get professional results (Linkedin Learning Jan 2020)
- Introduction to Reproduction (Coursera Jul 2019)
- Human Trafficking Awareness for the General Public (Lagunita: Stanford Online Dec 2018)
- Learning How to Learn: Powerful mental tools to help you master tough subjects (Coursera Oct
2018)
- Stanford Introduction to Food and Health (Coursera Sep 2017)
|
|