Hyunwoo Kim is the Head of AI Research at Newnal, having joined the company in November 2024. Prior to this, he was a Senior Research Expert and Principal Investigator at Zhejiang Lab, Hangzhou, China. Before his time at Zhejiang Lab, Dr. Kim worked at LG AI Research, LG Electronics, Kakao Corp., and Samsung Electronics, Seoul, Korea, as senior-level researchers and technical leaders. He has also held academic positions as an associate professor at the Beijing Institute of Technology, Beijing, China, and as an assistant professor at the Korean German Institute of Technology, Seoul, Korea. He received his Ph.D. degree from the School of Electrical and Computer Engineering at POSTECH, Pohang, Korea.
Dr. Kim has been actively engaged in computer vision and deep learning, publishing over 50 international journals and conference proceedings, along with US patents, accumulating over 3,200 citations (h-index = 27). He has received numerous prestigious awards, including the first prize in the CVPR 2020 CLVision Challenge, the 2020 LG Awards presented by LG Corp., and the 2006 iF Design Award in Germany. His work on face image retrieval has become an international standard in the MPEG-7 ISO/IEC, and his large-scale image retrieval method has been successfully commercialized. His current research interests include generative modeling, representation learning, video analysis and generation, and 3D vision and graphics.
Computer Vision, Deep Learning, Generative AI
LG Electronics
Beijing Institute of Technology
Kakao Corp.
Korean German Institute of Technology
Samsung Electronics
Doctor of Philosophy (Ph.D.), Electronic and Computer Engineering, POSTECH, Pohang, Korea
Thesis: Image Mosaicing and Super-Resolution of Dynamic Scenes (Advisor: Ki-Sang Hong)
Master's Degree (M.S.), Electrical and Electronic Engineering, POSTECH, Pohang, Korea
Thesis: Design of an Image Processor for Enlargement/Reduction using VHDL
Bachelor's Degree (B.S.), Electronic Communication Engineering, Hangyang University, Seoul, Korea
Learning Equi-angular Representations for Online Continual Learning (Minhyuk Seo, Hyunseo Koh, Wonje Jeung, Min Jae Lee, San Kim, Hankook Lee, Sungjun Cho, Sungik Choi, Hyunwoo Kim*, Jonghyun Choi*), CVPR 2024, June, 2024. (co-corresponding author)
Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization (Jihwan Jeong, Xiaoyu Wang, Michael Gimelfarb, Hyunwoo Kim*, Baher Abdulhai, Scott Sanner*), ICLR 2023, May 2023 [arXiv] (co-corresponding author)
Unsupervised Visual Representation Learning via Mututal Information Regularized Assignemnt (DH Lee, S Cho, H Kim, SY Chung), NeurIPS 2022, Nov 2022 [arXiv]
VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation (SH Han, S Hwang, SW Oh, Y Park, H Kim, MJ Kim, SJ Kim), CVPR 2022 Oral, June 2022 [arXiv] [GitHub]
Perception Prioritized Training of Diffusion Models (Jooyoung Choi, Jungbeom Lee, Chaehun Shin, Sungwon Kim, Hyunwoo Kim, Sungroh Yoon), CVPR 2022, June 2022 [arXiv]
Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization (Eunji Kim, Siwon Kim, Jungbeom Lee, Hyunwoo Kim, Sungroh Yoon), CVPR 2022, June 2022 [arXiv]
Online Continual Learning in Image Classification: An Empirical Survey (Z Mai, R Li, J Jeong, D Quispe, H Kim, S Sanner), Neurocomputing, Volume 469, 2022, Pages 28-51 [arXiv] [GitHub]
Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning (Z Mai, R Li, H Kim, S Sanner), CVPR 2021 Workshop on Continual Learning, CVPRW 2021 [ArXiv] [GitHub] [Video]
Online Class-Incremental Continual Learning with Adversarial Shapley Value (Dongsub Shim, Zheda Mai, Jihwan Jeong, Scott Sanner, Hyunwoo Kim, Jongseong Jang), AAAI-21, Feb 2021 [arXiv] [GitHub] [Blog]
Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation (Sam Sattarzadeh, Mahesh Sudhakar, Anthony Lem, Shervin Mehryar, KN Plataniotis, Jongseong Jang, Hyunwoo Kim, Yeonjeong Jeong, Sangmin Lee, Kyunghoon Bae), AAAI-21, Feb 2021 [arXiv] [Blog]
Batch-level Experience Replay with Review for Continual Leaning (Zheda Mai, Hyunwoo Kim, Jihwang Jeong, Scott Scanner), CVPR 2020 Workshop on Continual Learning in Computer Vision, Challenge Track (CVPRW ’20), 14th June 2020, Seattle, USA (Winner All categories - 1st place in all 3 tracks among 79 teams) [Result] [arXiv] [GitHub] [Slide] [Blog]
Learning Not to Learn: Training Deep Neural Networks with Biased Data (Byungju Kim, Hyunwoo Kim, Kyungsu Kim, Sungjin Kim, Junmo Kim), The Thirtieth IEEE/CVF Conference on Computer Vision and Pattern Recognition Main (CVPR’19), Long Beach, CA, June 16-21, 2019 [arXiv] [GitHub]
Winner of the CLVISION Continual Learning Challenge at CVPR 2020, June 2020
LG Awards, DX R&D, ”Best practice for AI-driven Problem Solving,” April 2020
iF Design Award 2006, XHT (Extendable Home Theater) – Interface for home A/V network solution, 2006
Email: eugene dot hwkim at gmail dot com
Google Scholar: https://scholar.google.com/citations?hl=en&user=5DfOhKwAAAAJ&view_op=list_works&sortby=pubdate
LinkedIn: https://www.linkedin.com/in/hyunwoo-k-b16460193/