Junsoo Lee
Artificial Intelligence Research Scientist, Generative Modeling, Computer Vision
Korea Advanced Institute of Science and Technology (KAIST)
NAVER WEBTOON AI
ljs93kr at gmail dot com (ljs93kr@gmail.com)
About Me
"Do it, like a Pro"
I currently work at NAVER WEBTOON Ltd. as a professional researcher of AI.
I acquired a master's degree in AI from Korea Advanced Institute of Science and Technology (KAIST), advised by Professor Jaegul Choo.
I am interested in finding ways that extract generalized and useful information (e.g., representation learning) without any labels (unsupervised / self-supervised) or in the very limited environment (semi-supervised), disentangle information according to its own purpose (e.g., image translation), and create an output with resepct to user's intention (e.g., conditional image generation / colorization).
#AI Research #Computer Vision #Generative Models #Machine Learning / Deep Learning #AI Engineering #Conditional Generation #Representation Learning #Self-supervised Learning #Colorization #Style Transfer #Python
News
[Mar 2021] I started a work at NAVER WEBTOON AI as research scientist.
[Sep 2020] I will present my studies, including my work, at AI conference hosted by DIT Center of SAMSUNG Electronics.
[Aug 2020] I presented our work (colorization) at KCCV'20 conference.
[Jul 2020] I started research internship at AI Lab Context part, KAKAO Enterprise Corp.
[Jul 2020] I presented work of my laboratory, including my work, at AI conference hosted by HYUNDAI Motor Corporation.
[Jun 2020] I presented our work (colorization) at CVPR'20 conference.
[Mar 2020] I started my MS course at Korea Advanced Institute of Science and Technology (KAIST).
[Mar 2019] I started my MS course at Korea University.
[Oct 2018] I started research at AI Research team, NAVER WEBTOON Corp.
[Apr 2018] I started research internship at Papago OCR team, NAVER Corp.
Publications
DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models
Sungnyun Kim*, Junsoo Lee*, Kibeom Hong, Daesik Kim, Namhyuk Ahn
Under-reviewed
[Paper]
Exploring to Decompose Identity of Image Animation into Structure and Attribute by Cross-identity Generation
Junsoo Lee, Gunhee Kim, Kibeom Hong, Daesik Kim
Under-reviewed
Guiding Users to Where to Give Color Hints for Efficient Interactive Sketch Colorization via Unsupervised Region Prioritization
Youngin Cho*, Junsoo Lee*, Soyoung Yang, Juntae Kim, Yeojeong Park, Haneol Lee, Jaegul Choo
accepted at WACV 2023
[Paper]
LPMM: Intuitive Pose Control for Neural Talking-Head Model via Landmark-Parameter Morphable Model
Kwangho Lee, Patrick Kwon, Myung Ki Lee, Namhyuk Ahn, Junsoo Lee
accepted at CVPRW 2023
[Paper]
Reference-based Image Composition with Sketch via Structure-aware Diffusion Model
Kangyeol Kim, Sunghyun Park, Junsoo Lee
accepted at CVPRW 2023
[Paper]
FlatGAN: A Holistic Approach for Robust Flat-Coloring in High-Definition with Understanding Line Discontinuity
Han Kim*, Chunggi Lee*, Junsoo Lee*, Dohyun Kim, Ganggin Lee, Mohyun Oh, Daesik Kim
Under-reviewed
Learning Representations by Contrasting Clusters While Bootstrapping Instances
Junsoo Lee*, Hojoon Lee*, Inkyu Shin, Jaekyoung Bae, InSo Kweon, Jaegul Choo
Under-reviewed
AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment
Kangyeol Kim, Sunghyun Park, Jaeseong Lee, Sunghyo Chung, Junsoo Lee, Jaegul Choo
accepted at ECCV 2022
[Paper]
Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation
Sunghyun Park*, Kangyeol Kim*, Junsoo Lee, Jaegul Choo, Joonseok Lee, Sookyung Kim, Edward Choi
accepted at AAAI 2021
[Paper]
Understanding Human-side Impact of Sequencing Images inBatch Labeling for Subjective Tasks
Ray Hong, Jungsoo Lee, Kyungmin Park, Junsoo Lee, Chaeyeon Chung, Dongjun Kim, Yunsug Lee, Minjae Kim, Mookyung Song, Yeonwoo Kim, Jaegul Choo
accepted at AAAI 2021
[Paper]
Simultaneous Recognition of Horizontal and Vertical Text in Natural Images Chankyu Choi, Youngmin Yoon, Junsoo Lee and Junseok Kim accpeted at ACCV 2018 [Paper]
Work Experiences
Kakao Enterprise Corp. July. 2020 - present
AI Lab, as Research Internship
- Unsupervised (self-supervised) Representation Learning
- Semi-supervised Representation Learning
NAVER Webtoon Corp. Oct. 2018 - Feb. 2019
AI Research, as Full-Time Researcher
- Organized a workshop of comics at ICCV'19
- Research on visual-language problems
NAVER Corp. Apr. 2018 - Oct. 2018
Papago OCR, as Research Internship
- Optical character recognition (OCR)
- Developed a synthetic data generator for training the engine
Xinapse Corp. Apr. 2018 - Oct. 2018
NLP Engineering, as Research Internship
- Research on topic modeling
- Developed a chat-bot system