Kyle Min
Principal Applied Scientist at Oracle
Redmond, Washington, United States
Summary
👤
Senior🎓
Top SchoolKyle Min is a Principal Applied Scientist based in Redmond with nine years of experience specializing in computer vision, video understanding, and human action recognition. He holds a PhD in Computer Vision from the University of Michigan and has driven research-to-production impact across academia, industry labs, and healthcare deployments. At Intel Labs he led graph-based audio-visual diarization and safety research for generative models, contributed to video generative modeling and transformer sparsification, and co-authored 10+ publications including work that earned top rankings on ActivityNet and Ego4D. Currently at Oracle he focuses on video generative models and multimodal LLMs within OCI, building on prior successes in action segmentation, motion controllability profiling, and a patent for industrial workflow analysis. Kyle combines deep theoretical research with practical systemization—turning state-of-the-art models into optimized, hardware-aware solutions. He brings a rare blend of hands-on algorithm development, production-grade deployment experience, and cross-disciplinary collaboration.
9 years of coding experience
11 years of employment as a software developer
Bachelor's degree Electrical Engineering and Computer Science, Bachelor's degree Electrical Engineering and Computer Science at Seoul National UniversityDoctor of Philosophy - PhD Computer Vision, Doctor of Philosophy - PhD Computer Vision at University of MichiganEarly graduation Physics, Early graduation Physics at Gyeonggi Science High School for the Gifted (경기과학고등학교)
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (72)
action-localization10
data-cleaning10
video-understanding10
computer-vision10
graph-neural-network10
visualization10
encoder-decoder10
pytorch-geometric10
adversarial-learning9
active-learning9
developer-tools9
object-detection9
feature-extraction9
python9
deep-learning9
Programming languages (5)
Github contributions (5)
MichiganCOG/TASED-Net
Aug 2019 - Mar 2021
Temporally-Aggregating Spatial Encoder-Decoder Network for Video Saliency Detection (ICCV 2019)
Contributions:11 commits, 11 pushes, 1 branch in 1 year 7 months
encoder-decodervideo-saliencyiccviccv2019s3d
SRA2/SPELL
Jul 2022 - Nov 2022
Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection (ECCV 2022)
Contributions:11 commits, 8 pushes, 19 comments in 4 months
active-speaker-detectionava-dataseteccveccv2022graph-learning
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.