Please sign up to attend MediaPipe (
https://mediapipe.dev) talk below
https://mediapipe.page.link/seattle2020Date: 13 Feb 2020, 5pm-6pm Pacific Standard Time (PST)
Where: Google Building Waterside
651 N. 34th St., Seattle, WA 98103
Talk is at 2nd floor in room called "Abacus"
Any questions: email
mgyong@google.comMediaPipe: Building real time cross platform (mobile, web, edge, desktop) video audio ML pipelines
Abstract
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
https://mediapipe.page.link/handgoogleaiblogHadon Nash is a senior software engineer in Google Research in AI Perception. Hadon has been responsible for Google's MediaPipe Framework for several years. Before that he developed the Live Experiment Framework for Google Search Ads. Before that he worked at Qbit LLC developing advanced lossless compression algorithms, at Parabon Inc. developing early cloud computing platforms, at IBM Global Systems, and at Apple Computer researching Agoric adaptive algorithms. Hadon graduated with MS in CS from George Mason University in Fairfax Virginia.