Career Profile

I’m pursuing master degree at Korea Advanced Institute of Science and Technology (KAIST). While doing research in high-level software algorithm, I felt a lot of inconvenience on deep-learning training time and memory issue. These days, a deep neural network requires large memory and training time even though they adopt a parallel computing approach. Therfore, after finishing master degree, I am planning to delve into hardware deep learning accerleration.

News

December 2019
I successfully defended my master's thesis!
December 2019
Two papers accepted at WACV2020
November 2019
Two papers submitted at CVPR2020
July 2019
Start AI research internship program in Kakao Corp.
July 2019
Paper accepted as poster at BMCV2019 in Cardiff, UK
September 2018
Paper accepted as spotlight at WACV2019 in Cona, Hawaii
May 2018
Paper accepted as oral at VCIP2018 in Taichung, Taiwan
February 2018
I finished my undergaduate course and got 2nd ranked in school of engineering

Publications

RPM-Net: Robust Pixel-Level Matching Networks forSelf-Supervised Video Object Segmentation
Youngeun Kim, Seokeon Choi, Hankyeol Lee, Taekyung Kim, and Changick Kim
IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
RPM-Net: Robust Pixel-Level Matching Networks forSelf-Supervised Video Object Segmentation
Youngeun Kim, Seokeon Choi, Hankyeol Lee, Taekyung Kim, and Changick Kim
IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
Combinational Class Activation Maps for Weakly Supervised ObjectLocalization
Seunghan Yang, Yoonhyung Kim, Youngeun Kim, and Changick Kim
IEEE Winter Conference on Applications of Computer Vision (WACV), 2020
Bilinear Siamese Networks with Background Suppression for Visual Object Tracking
Hankyeol Lee, Seokeon Choi, Youngeun Kim, and Changick Kim
British Machine Vision Conference (BMVC), 2019
CNN-based Semantic Segmentation Using Level Set Loss
Youngeun Kim, Seunghyeon Kim, Taekyung Kim, and Changick Kim
IEEE Winter Conference on Applications of Computer Vision (WACV), 2019
Weakly Supervised Semantic Segmentation Using Color Adjacency Loss
Youngeun Kim, Taekyung Kim, Seunghyeon Kim, and Changick Kim
IEEE International Conference on Visual Communications and Image Processing (VCIP), 2018

Education

Master Degree

2018 - current
KAIST (Daejoen, Korea)

Master degree in Electrical Engineering

Bachelor Degree

2012 - 2018
Sogain University (Seoul, Korea)

Bachelor degree in Electronic Engineering #-During pursing my Bachelor degree, I learned overall concept of Computer Architecture and showed outstanding performance in the class. Moreover, I experienced designing an digital circuit in Digital Signal Processing class. In this class, I designed basic filter system by FPGA programming using Verilog. Furthermore, I also made a circuit and coded on the Microprocessor in Microprocessor Laboratory Class. At that time, I designed the device for learning braille by connecting LCD, dot buttons, and processor.

Experiences

AI research internship

June 2019 - Present
Kakao Corporation, Korea

#-Computer Vision #-Deep Learning

Honors

Dean’s List (Best student performance award) - Spring 2015, Fall 2015, Spring 2016, Fall 2016

Skills & Proficiency

Python

PyTorch

Tensorflow

VHDL / Verilog

Matlab

C/C++