Back To Schedule
Thursday, October 10 • 3:30pm - 3:55pm
OPEN TALK (AI): Building Multimodal (Video, Audio) Ml Applications for Mobile & Edge Devices

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Video, audio (multimodal) mobile and edge use cases that utilize machine learning models (eg Tiktok, Shazam, Google Home Hub) are becoming more common. However, creating these multimodal ML applications are challenging as developers need to deal with real time synchronization of time series data during model inference and doing it cross platform on mobile and edge devices.
Google open sourced in Jun 2019, MediaPipe (https://mediapipe.dev), a cross platform applied machine learning pipeline framework that simplifies the development process. My talk will be introducing open source MediaPipe framework, walking through mobile and edge (EdgeTPU coral) demos and getting developers started on building multimodal ML applications

Video of MediaPipe - face and gaze detection running ML accelerated on EdgeTPU

AI DevWorld 2019 Speakers
avatar for Ming Yong

Ming Yong

Product Manager, Google Research Perception, Google
Ming Yong is a Product manager in Google Research Perception Research leading open source efforts in computer vision. In Google, he was previously product manager in Google Search and product lead for mobile video ad formats. Before Google, Ming was cofounder Socialwok, an enterprise... Read More →

Thursday October 10, 2019 3:30pm - 3:55pm PDT
AI DevWorld -- Main Stage Theater