Hyogun Lee
Scholar

Hyogun Lee

Google Scholar ID: tBIhh3EAAAAJ
Korea Institute of Science and Technology (KIST)
Long-term video understandingMulti-modal Large Language ModelsMLOps
Citations & Impact
All-time
Citations
7
 
H-index
2
 
i10-index
0
 
Publications
5
 
Co-authors
8
list available
Resume (English only)
Academic Achievements
  • Selected Publications:
  • - Infusing Environmental Captions for Long-Form Video Language Grounding, 2024.
  • - GLAD: Global-Local View Alignment and Background Debiasing for Unsupervised Video Domain Adaptation with Large Domain Gap, In the Winter Conference on Applications of Computer Vision (WACV), 2024.
Research Experience
  • Working at Vision and Learning Lab, Kyung Hee University.
Education
  • Feb, 2024: M.Eng in Computer Science and Engineering, Kyung Hee University, Korea. Aug, 2021: B.Eng in Electronic Engineering, Kyung Hee University, Korea.
Background
  • Research Interests: Long-Term Video-Language Grounding, Multi-modal Large Language Models (MLLMs), Unsupervised Domain Adaptation. Post Master's Researcher of Computer Science and Engineering at Kyung Hee University, working with Prof. Jinwoo Choi.
Miscellany
  • Technical Skills: Python, Linux Shell Scripting, C/C++, HTML/CSS/JS, PyTorch, PyTorch Lightning, Hydra, MLOps tools like Slurm, Ansible, DeepOps, Django, CUDA, Docker.
  • Human Languages: Korean (native), English (proficient).