Edge AI in Action: Technologies and Applications

Jun 11, 2025·
Fabricio Batista Narcizo
Fabricio Batista Narcizo
,
Elizabete Munzlinger
,
Sai Narsi Reddy Donthi Reddy
,
Shan Ahmed Shaffi
· 0 min read
Image credit: CVPR 2025
Abstract

Edge AI refers to the deployment of artificial intelligence models directly on edge devices—such as smartphones, cameras, sensors, drones, and wearables—enabling them to perform inference locally without continuous reliance on the cloud. This paradigm offers several significant benefits, including reduced latency, enhanced privacy, increased responsiveness, and improved energy efficiency.


However, building performant AI systems for edge environments introduces unique challenges. These include model compression, quantization, distillation, pruning, and runtime optimization, as well as effective orchestration across heterogeneous hardware in hybrid edge–cloud architectures.


In this CVPR 2025 tutorial, we offered a hands-on and practice-oriented guide to designing, optimizing, and deploying deep learning models for edge AI. Focusing on computer vision tasks, we explored real-world use cases, including hand gesture recognition, object detection, and large language models. The tutorial emphasized multimodal AI, integrating inputs such as video, images, and text to enable intelligent, interactive systems.


We demonstrated the use of leading tools and frameworks, including ONNX, Qualcomm SNPE, TensorFlow Lite for Android, vLLM, and Ollama, across a range of hardware platforms, such as Jabra intelligent cameras, Qualcomm dev boards, Android mobile phones, and NVIDIA Jetson AGX Orin. Attendees gained actionable insights into the end-to-end pipeline of edge AI, from model design to real-time deployment.

Date
Jun 11, 2025 11:50 AM — Jun 15, 2025 12:10 PM
Event
Location

Music City Center

201 Rep. John Lewis Way S, Nashville, 37203 Tennessee

events
Fabricio Batista Narcizo
Authors
Senior AI Research Scientist
Fabricio Batista Narcizo is a Senior AI Research Scientist in the Video Technology department at GN Hearing A/S (Jabra) and a Part-Time Lecturer and Course Manager at the IT University of Copenhagen (ITU). He received his Ph.D. degree in Computer Science from the ITU in 2017, his M.Sc. degree in Electronic & Computer Engineering from the Aeronautics Institute of Technology (ITA) in 2008, and his B.Sc. degree in Computer Science from the University of Western Santa Catarina (UNOESC) in 2005. His research interests lie in computer vision, image analysis, artificial intelligence, data science, data mining, machine learning, edge AI, and human-computer interaction, with a particular interest in eye-tracking.