[C28] M. S. Ryoo, Kiyoon Kim, Hyun Jong Yang*, “Extreme low resolution activity recognition with multi-Siamese embedding learning,” AAAI Conference on Artificial Intelligence (one of the top AI conferences, acceptance rate=24.6%), New Orleans, Louisiana, Feb. 2018. [arXiv] Abstract This paper presents an approach for recognition of human activities from extreme low resolution (e.g., 16×12) videos. Extreme low resolution… Continue reading
Deep learning-based activity/face recognition based on extreme low resolution at CVPR 2017 Technology introduction Our real-time tech demo
Hyun Jong Yang founds a startup company, EgoVid Inc. EgoVid studies privacy-preserving (safe) machine learning for signal processing and computer vision. See here.
(T10) Machine Learning and Its Application in Communications, Dec. 2016.
AiSLab members visited U.C. Berkeley to exchange ideas about making a start-up company from Dec. 2016~Mar. 2017.
[P11] Multi-viewpoint camera system for active situation recognition, UNIST (KR 10-2015-0149546).
[C27] M. S. Ryoo*, Brandon Rothrock, Charles Fleming, Hyun Jong Yang*, “Privacy-preserving human activity recognition from extreme low resolution,” AAAI Conference on Artificial Intelligence (one of the top AI conferences, acceptance rate=24.6%), San Francisco, CA, Feb. 2017. [arXiv] Abstract Privacy protection from unwanted video recordings is an important societal challenge. We desire a computer… Continue reading