Machine Learning & Vision Lab

Hyunwoo J Kim (김현우) Ph.D.


Assistant Professor


Machine Learning and Vision LabDepartment of Computer Science and EngineeringCollege of Informatics, Korea Universityemail: hyunwoojkim@korea.ac.krtel: +82-2-3290-4604Web@UW-Madison[CV]

About Me

Hyunwoo J. Kim joined Korea University in March 2019 as an assistant professor. Prior to the position, he worked at Amazon Lab126 in Sunnyvale California. In 2017, he earned the Ph.D. in the Department of Computer Sciences at University of Wisconsin-Madison (Ph.D. minor: statistics) under the supervision of Dr. Vikas Singh. In 2013, he completed his internship in the Machine Learning Analytics Team at Amazon in Seattle Washington.

His research interests include statistical machine learning, manifold statistics and deep learning for structured data in computer vision and medical imaging. He collaborated with the Wisconsin Alzheimer's Disease Research Center (ADRC) at UW-Madison. His main focus is machine learning and computer vision for visual understanding and he has been actively publishing AI venues (e.g., CVPR, ICCV, ECCV, NIPS, ICML).

News

  • [New] We have openings for graduate students, and undergraduate interns. If interested, email me.
  • [2019/03/19] Upcoming Talk on Computer Vision and Research at MLV Lab. 5PM Woojung Hall #601.
  • [2019/03] Computer Vision (AAA534) has no more seat.
  • [2018/04] Poster presentation at AMLC (Amazon Machine Learning Conference, "Amazonian" only).
  • [2017/09] Talk at DeepMind, Google.

Machine Learning & Vision Lab

The Machine Learning and Vision Lab (MLV) at Korea University is directed by Hyunwoo J Kim. We are tackling fundamental open problems in machine learning and computer vision to achieve a deep understanding of the visual world. High-level visual perception involves automated image and video analysis, computational geometry, and visual reasoning. Highly structured knowledge, images and videos lead us to study the underlying non-Euclidean space and generalize models, including deep neural networks, to manifolds, and graphs. We develop efficient and scalable solutions to handle real-world visual data in large scale as well as in resource-limited environments.