Chulwoo Pack
Assistant Professor at South Dakota State University
Lincoln, Nebraska, United States
Summary
👤
Senior🎓
Top SchoolChulwoo Pack is an Assistant Professor in EECS at South Dakota State University and a Ph.D. graduate from the University of Nebraska–Lincoln with eight years of experience bridging computer vision, multimodal learning, and document understanding. His research goal is to build foundational computer vision systems that support human users, with active work in image processing, medical image analysis, visual question answering, RAG, and explainable AI. He has a strong applied research background—developing deep learning models for neuroimaging segmentation, eye-tracking–based task prediction, and large-scale historical document clustering—and has translated that work into practical tooling and repositories for real datasets. As director of the Multimodal Intelligence Lab, he combines information retrieval and multimodal techniques to advance human-centered AI, drawing on hands-on experience from a Library of Congress research internship and prior web development roles. Notably, his work spans both cultural heritage and clinical domains, showing an uncommon breadth in applying multimodal methods to diverse, real-world collections.
9 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Nebraska-LincolnMaster of Science (MS), Computer Science, 3.85, Master of Science (MS), Computer Science, 3.85 at South Dakota State University
English, Korean
Github Skills (12)
image-segmentation9
textual9
localization8
image-processing8
multimodal6
feature-extraction6
algorithm4
segmentation4
ocr3
neural-network3
tensorflow3
ocr-engine2
Programming languages (4)
Github contributions (5)
chulwoopack/docstrum
Feb 2018 - Apr 2018
Contributions:23 commits, 21 pushes, 4 branches in 1 month
docstrumimage-segmentationdocument-image-analysisimage-processing
chulwoopack/gravity-map
Apr 2021 - Jan 2022
Visual Domain Knowledge-based Multimodal Zoning Textual Region Localization in Noisy Historical Document Images
Contributions:28 commits, 6 PRs, 24 pushes in 9 months
localizationmultimodaltextual
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.