Jongchan Park
Research Scientist @Lunit Inc.
jcpark [at] lunit.io
CV | Github | Google Scholar
I received my BS degree in Computer Science, and my MS degree in Electrical Engineering from KAIST. During my MS degree, I was advised by Prof. In So Kweon. Spent most of my childhood in China.
Interested in object recognition with deep learning.
Selected Publications
(* equal contribution)
Using Self-Supervised Pretext Tasks for Active Learning
John Seon Keun Yi*, Minseok Seo*, Jongchan Park, Dong-Geol Choi
European Conference for Computer Vision (ECCV) 2022
A Self-Supervised Sampler for Efficient Action Recognition: Real-World Applications in Surveillance System
MinSeok Seo, Donghyeon Cho, SangWoo Lee, Jongchan Park, Daehan Kim, Jaemin Lee, Jingi Ju, Hyeoncheol Noh, and Dong-Geol Choi
IEEE Robotics and Automation Letters (RA-L), presented at IEEE International Conference on Robotics and Automation (ICRA) 2022
Reducing Domain Gap by Reducing Style Bias
Hyeonseob Nam*, HyunJae Lee*, Jongchan Park, Wonjun Yoon, Donggeun Yoo
Conference on Computer Vision and Pattern Recognition (CVPR) 2021, oral
Development and validation of a deep learning algorithm detecting 10 common abnormalities on chest radiographs
Ju Gang Nam, Minchul Kim, Jongchan Park, Eui Jin Hwang, Jong Hyuk Lee, Jung Hee Hong, Jin Mo Goo, Chang Min Park
European Respiratory Journal (IF 12.339)
Learning Visual Context by Comparison
Jongchan Park*, Minchul Kim*, Seil Na, Chang Min Park, and Donggeun Yoo
European Conference for Computer Vision (ECCV) 2020, spotlight (top 5% among submission)
Sequential Feature Filtering Classifier
Minseok Seo*, Jaemin Lee*, Jongchan Park, and Dong-Geol Choi
arXiv 2020
A Simple and Light-weight Attention Module for Convolutional Neural Networks
Jongchan Park*, Sanghyun Woo*, Joon-Young Lee, and In So Kweon
International Journal of Computer Vision (IJCV)
CBAM: Convolutional Block Attention Module
Jongchan Park*, Sanghyun Woo*, Joon-Young Lee, and In So Kweon
European Conference for Computer Vision (ECCV) 2018
BAM: Bottleneck Attention Module
Jongchan Park*, Sanghyun Woo*, Joon-Young Lee, and In So Kweon
29TH British Machine Vision Conference (BMVC), oral
Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning
Jongchan Park, Joon-Young Lee, Donggeun Yoo, and In So Kweon
Conference on Computer Vision and Pattern Recognition (CVPR) 2018
Work Experiences
Lunit Inc. as a research scientist. Mar. 2018 ~
Lunit Inc. as a research intern. Oct. 2014 ~ Jul. 2015
MyDrives Inc. as a software engineer. Sep 2013 ~ Sep. 2014
Academic Services
2022: CVPR, ECCV reviewer
2021: AAAI, WACV, CVPR, TPAMI reviewer
2020: CVPR, AAAI, BMVC reviewer
2019: CVPR, ICCV, ICCVW (VRMI), MICCAI reviewer
Honors & Awards
VisDA 2019 Challenge - SSDA track, Winner
24th Samsung HumanTech Paper Award (w/ BAM: Bottleneck Attention Module), Gold Prize (top 0.5%, $10,000 prize)
NVIDIA Deep Learning Contest 2016 (w/ Thermal image enhancement using deep learning algorithm), 1st place
Patents
Apparatus for predicting metadata of medical image and method thereof (KR registered, multiple countries pending)
Method and apparatus for estimation of tire-road type by using ultrasonic signal (pending)
Method and Apparatus for bottleneck attention modules in deep convolutional neural networks (pending)
Method and Apparatus for thermal image enhancement using deep learning algorithm (domestic)
Method for moving image service of golf, system and computer-readable medium recording the method (domestic)