Inventors
Deep Patel, Giovanni Milione, Kai Li, Farley Lai, Erik Kruus
Publication date
2024/8/15
Patent office
US
Application number
18439242
Description
Methods and systems of training a machine learning model include identifying an object or person related to an action in a first video. The object or person is copied from the first video to a second video to generate a third video. A machine learning model is trained using the first video and the third video.
Scholar articles
D Patel, G Milione, K Li, F Lai, E Kruus - US Patent App. 18/439,242, 2024