The session focuses on discussing the various research work in the video understanding and about the TwelveLabs. After understanding the various emerging usecases of the Prompting with the video and the functionality of the engines of the multimodality. The Hands-on session would be focused on building the application on talking to the youtube video and doing more than the transcription and building for the dynamic and various usecases at the same time.
Duration of the Session - 50-60 min
Agenda of the Session
Overview of the Video Understanding
Understanding the working of the multimodal architecture
About Engines by TwelveLabs
Emerging Usecases and Products
Building the application on streamlit for video understanding
QnA
I'm currently working on the PPT, you can checkout my blog -
https://hrishikesh332.hashnode.dev/chapter-3-hands-on-ai-video-note-app-twelvelabs