Next-Generation Computer Vision Capabilities with Project Florence

Adina Trufinescu joins Seth today to introduce Introduce Azure Cognitive Service for Vision and the next-generation Computer Vision Capabilities with Florence and walk us through some of the new features! Chapters: 00:00 AI Show begins 00:16 Welcome and Intros 00:58 What is Project Florence 01:59 How does a multi-modal model work 08:07 Demo begins 09:05 Dense captions 10:28 Searching for photos with natural language 12:54 Try with your own images 16:40 Video summary and frame locator 21:40 Training dataset 24:43 Learn more 25:25 Wrap Resources: http://aka.ms/VisionStudio https://aka.ms/CognitiveService/Vision Connect: Seth | https://twitter.com/sethjuarez Cassie | https://twitter.com/Cassieview Watch on-demand at https://aka.ms/AIShow/OnDemand Subscribe to the AI Show: https://aka.ms/AIShowsubscribe AI Show Live Playlist: https://aka.ms/AIShowPlaylist Join us every Monday, for an AI Show livestream on YouTube https://aka.ms/AIShowLive