Paul J. Shin, PhD is a senior manager for Vision AI at NVIDIA. He leads various projects on computer vision and perception modules and tools for Vision AI for DeepStream and Metropolis (including GPU-accelerated multi-object trackers). Previously, Paul led the R&D group at a retail analytics company where he architected and developed the multi-camera multi-object tracking pipeline including multi-modal sensor fusion algorithms and the end-to-end real-time edge AI processing pipeline for 2000+ smart cameras connected to the cloud using AWS IOT for real-time in-store shopper behavior analytics. He earned a PhD in computer vision and wireless sensor networks from Purdue University in 2013 and a B.E. from Korea University. He holds 17 pending and issued patents with six peer-reviewed publications in top computer vision conferences and journals.