Youngwook Paul Kwon

Computer Vision + Deep Learning
CV | GitHub | Linkedin | Google Scholar

I’ve been fascinated in various theories of computer vision and deep learning. Plus, I've also enjoyed the deeper understanding of the physical world. These combined interests led me to study both computer science and mechanical engineering. I received double B.S. at Seoul National University (CS+ME), M.S. at UC Berkeley (CS), and Ph.D. at UC Berkeley (ME concentrated in computer vision, especially the topics of image feature description and matching). Several internships at Lawrence Livermore National Laboratory ignite my research on low-level image processing such as feature detection and description. Currently at Phantom AI, I've worked on high-level perception such as object detection (2D/3D) in the field of autonomous driving. In short, here are my all-time questions: How can I help machines to see/think/act better, and given my humble knowledge, how can I contribute to the society in a positive way?

Email theorem: \(e=x@y\) where \(x=\)"young" and \(y=\)"berkeley.edu"   

Research

(* equal contribution)

Myoung Hwan Oh, Min Gee Cho, Dong Young Chung, Inchul Park, Youngwook Paul Kwon, Colin Ophus, Dokyoon Kim, Min Gyu Kim, Beomgyun Jeong, X. Wendy Gu, Jinwoung Jo, Ji Mun Yoo, Jaeyoung Hong, Sara McMains, Kisuk Kang, Yung-Eun Sung, A. Paul Alivisatos, Taeghwan Hyeon
Nature (cover), 2020
Not my typical area but discussion over coffee ends up with contribution to Nature cover!
Kiwoo Shin*, Youngwook Paul Kwon*, Masayoshi Tomizuka
arXiv, 2018
2nd place @ KITTI 3D detection benchmark!
videoproject
Deep Traffic Light Detection for Self-driving Cars from a Large-scale Dataset
Jinkyu Kim, Hyunggi Cho, Myung Hwangbo, Jaehyung Choi, John Canny, Youngwook Paul Kwon
IEEE International Conference on Intelligent Transportation Systems (ITSC), 2018
pdf
A Novel Trajectory Prediction of Traffic Participants for Autonomous Lane Change Assistance
Donghan Lee*, Youngwook Paul Kwon*, Jinkyu Kim, Jongsang Suh
International Symposium on Advanced Vehicle Control (AVEC), 2018
pdf
Donghan Lee*, Youngwook Paul Kwon*, Sara McMains, J. Karl Hedrick
IEEE International Conference on Intelligent Transportation Systems (ITSC), 2017
pdf
Chengwei Zhang, Youngwook Paul Kwon, Julia Kramer, Euiyoung Kim, Alice Merner Agogino
Journal of Mechanical Design (JMD), 2017
pdf
Chengwei Zhang, Youngwook Paul Kwon, Julia Kramer, Euiyoung Kim, Alice Merner Agogino
ASME International Design Engineering Technical Conferences and Computers and Information in Engineering Conference (IDETC/CIE), 2017
pdf
Youngwook Paul Kwon, Sara McMains
Neural Information Processing Systems (NIPS) workshop "Reliable Machine Learning in the Wild", 2016
pdf
Youngwook Paul Kwon, Hyojin Kim, Goran Konjevod, Sara McMains
IEEE International Conference on Image Processing (ICIP), 2016
pdfproject
Sushrut Pavanaskar, Sushrut Pande, Youngwook Paul Kwon, Zhongyin Hu, Alla Sheffer, Sara McMains
Journal of Manufacturing Processes (JMP), 2015
Youngwook Paul Kwon, Sara McMains
ACM Learning at Scale (L@S), 2015
pdf
Youngwook Paul Kwon
MS thesis, EECS at UC Berkeley, 2014

Some Projects

(ongoing, personal, course)

The paper has insufficient explanation about their algorithm. My interpretation & derivation.
Personal fun computational photography project.
Can you guess how I create this?
twix

Patents

Youngwook Paul Kwon, Phantom AI Inc.
US 11714424 B2, 2021
Youngwook Paul Kwon, Phantom AI Inc.
US 11670173 B2, 2023

Teaching

2014S ME101, High Mix/Low Volume Manufacturing (Graduate Student Instructor), UC Berkeley

2013F E28, Visualization and Graphics for Design (Reader), UC Berkeley