I am a Senior Research Scientist at Google Research, working in computer vision and machine learning. Most recently, I focus on developing on-device techniques for mobile products, such as Google’s first Face Unlock on Pixel 4/4XL (2019).
Prior to Google, I was a Deep Learning Scientist at Apple, taking a major role of algorithm development for on-device technology, including Apple’s first Face ID shipped with iPhone X (2017), real-time camera features (2018) shipped with decedent devices (eg, XR, XS, XS Max) and next-gen products. Before Apple, I was a research staff in the Robotics Institute at Carnegie Mellon University on Aug. 2010–2013, and received my Ph.D. from the same institute on Jan. 2017.
I (co-)authored over 30 publications in leading journals and conferences in computer vision and machine learning. I led the early development of IntraFace, an automated face analysis software that won the Best Demo Award in IEEE Conference on Automatic Face and Gesture Recognition (AFGR) 2015. A spinoff of IntraFace, FacioMetrics, was later acquired by Facebook on Nov. 2016. I also serves as an Area Chair on AFGR 2018–2019 and ICMI 2019.
Ph.D. in Robotics
Carnegie Mellon University
B.S. in Computer Science
National Cheng Kung University
Jaymo Kang (UC Berkeley), 2018
“Image Domain Transfer using Unpaired Image-to-Image Translation”