Pilhyeon Lee
Assistant Professor at Inha university
Seoul, South Korea
Summary
👤
Senior🎓
Top SchoolPilhyeon Lee is an Assistant Professor at Inha University leading the Multimodal AI Lab, with a decade of experience in computer vision, video understanding, multimodal learning, and weakly-supervised methods. He holds a PhD in Computer Vision from Yonsei University and a strong academic foundation from Chung-Ang University (Magna Cum Laude). His research blends rigorous academic inquiry with practical engineering—evident from contributions to open-source EEG-based deep learning (Deep-BCI) and a stint at Microsoft Research Asia and NAVER. Pilhyeon’s work often focuses on bridging modalities and domain adaptation (e.g., MMD loss for subject-adaptive EEG models), producing systems that perform in real-world, noisy settings. Based in Seoul, he combines lab leadership with active collaboration across industry and academia to translate multimodal research into usable tools.
10 years of coding experience
2 years of employment as a software developer
Bachelor's degree, Computer Science & Engineering, Honored Magna Cum Laude (4.18/4.5), Bachelor's degree, Computer Science & Engineering, Honored Magna Cum Laude (4.18/4.5) at Chung-Ang UniversityDoctor of Philosophy, Computer Vision, Doctor of Philosophy, Computer Vision at Yonsei University
Github Skills (16)
pytorch10
machine-learning10
gru10
deep-learning10
python10
preprocess9
modeling9
model-driven-development9
model-driven9
preprocessing9
dataprep9
data-preprocessing9
model-building9
data-loading9
data-science8
Programming languages (2)
Github contributions (5)
DeepBCI/Deep-BCI
Oct 2021 - Jan 2023
An open software package to develop BCI based brain and cognitive computing technology for recognizing user's intention using deep learning
Role in this project:
ML Engineer
ML EngineerContributions:16 commits, 13 pushes, 1 comment in 1 year 3 months
Contributions summary:Pilhyeon contributed code related to a subject-adaptive EEG-based visual recognition system using deep learning. The commits include the addition of data loading, model definition, and training scripts. These files suggest the development of a recurrent neural network (GRU) model for processing EEG data and implementing a training loop with validation and testing stages. The user is also working with a MMD loss function.
brainssveperpdeep-learningbci
Pilhyeon/WTAL-Uncertainty-Modeling
Jun 2020 - Jun 2021
Official Pytorch Implementation of 'Weakly-supervised Temporal Action Localization by Uncertainty Modeling' (AAAI-21)
Contributions:45 commits, 2 PRs, 43 pushes in 1 year
pytorchtemporal-action-localizationsupervisedtemporaluncertainty
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.