Twelve Labs: Building Multimodal Video Foundation Models for Better Understanding

‍

VP Land sits down with Soyoung Lee from Twelve Labs, a company building multimodal video foundation models that can understand everything inside a video. Their AI technology is set to revolutionize the way creators and businesses search, analyze, and manage their video content.

‍

⏱ CHAPTERS

‍00:00 Intro

‍00:20 What is Twelve Labs?

‍01:07 Building video-first AI models

‍02:36 Twelve Labs' unique approach

‍03:49 Applications of Twelve Labs' technology

‍06:00 A single, powerful model

‍06:57 Image and audio-based video search

‍08:08 AI in the media landscape

‍

📰 CREDITS

Producer & Host: Joey Daoud

Production Manager: Steve Regalado

Director of Photography: Justin Guo

Editors: Kirill Slepynin & Jan Gonzales

Graphic Designer: Kristina Leongard