Published research projects related to human action recognition, anomaly detection, small object detection, geolocalization, and medical imaging in top venues such as CVPR, ICRA, AAAI, WACV, CVIU, MICCAI, etc. Awarded the Facebook-CV4GC research award in 2019 and a Google Research scholar in 2023. Served as an Area Chair for Neurips 2024, WACV 2024, CVPR 2024, and other conferences.
Research Experience
Spent one year as a Principal Machine Learning Engineer at Hazenai, mainly working on designing and implementing improved multiple object tracking and robust traffic phase detection. Worked on projects from various companies and organizations including IARPA, DTS, NIJ, Xerox (USA), Facebook Research (US), Google Research (US), Samsung (South Korea), and Hazen.ai (Saudi Arabia).
Education
MS from Seoul National University (ranked 27th best university in the world at that time) and Ph.D. from the Center for Research in Computer Vision (6th best Computer vision research group in the US), University of Central Florida, USA, under the supervision of Mubarak Shah.
Background
A US-trained Computer Vision engineer (Ph.D.) with over 12 years of extensive hands-on experience in Computer Vision and Machine Learning. Specifically, I have been analyzing videos and images using supervised, weakly supervised, and unsupervised machine learning techniques.
Miscellany
Media coverage: Live Interview at C42; Introductory Video by ITU Media Team; Article published in NewScientist regarding our CVPR-2018 paper.