This lecture is for everyone who has an understanding of how deep neural network works.
The purpose of this session is to do an overview for those who began their way in video processing using deep learning.
We will review the common challenges and some of the unique techniques which we can use.
During the lecture we will cover the following topics:
What are the common use cases in the video domain?
The challenges that come with video processing and tips about how to handle them.
What are the common architectures that can identify the different patterns in videos?
How to exploit the video data structure with self-supervised techniques in order to create better baseline weights
Review of solutions for for “Video Summarization” & “Scenes highlighting”
Code demonstration 🤓
About the lecturer:
Ron Weiner is the Co-Founder & CEO of Give & Tech non-profit organization.
An AI researcher and Consultant (AiVF, Cor-e, Stayhome, ICV).
8200 alumni Bachelor of Computer and Cognition science at the OpenU.
Work with data in the past 9 years.