Paul Shin

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.
Avatar photo

Posts by Paul Shin

Computer Vision / Video Analytics

Advance Video Analytics AI Agents Using the NVIDIA AI Blueprint for Video Search and Summarization

Vision language models (VLMs) have transformed video analytics by enabling broader perception and richer contextual understanding compared to traditional... 15 MIN READ
Computer Vision / Video Analytics

Mitigating Occlusions in Visual Perception Using Single-View 3D Tracking in NVIDIA DeepStream

When it comes to perception for Intelligent Video Analytics (IVA) applications such as traffic monitoring, warehouse safety, and retail shopper analytics, one... 8 MIN READ
Computer Vision / Video Analytics

State-of-the-Art Real-time Multi-Object Trackers with NVIDIA DeepStream SDK 6.2

When you observe something over a period of time, you can find trends or patterns that enable predictions. With predictions, you can, for example, proactively... 9 MIN READ