YouTube is experimenting with a new machine learning technology that reformats video shot in landscape mode into square or vertical formats, based on how the viewer is watching YouTube.
The Google-owned video platform said its ML model detects key elements in the video—faces, key objects, logos, motion, text—and breaks that video into scenes, ensuring that those key elements appear properly in the reformatted video.
The new technology is aimed at benefiting advertisers that may not have the dedicated resources to create multiple assets for their campaigns.
The option is currently available for application campaigns, with Performance Max and video action campaigns to follow shortly.
YouTube
![AW+ AW+](https://cdn.statically.io/img/www.adweek.com/wp-content/uploads/2024/06/aw-plus.png)
WORK SMARTER - LEARN, GROW AND BE INSPIRED.
Subscribe today!
To Read the Full Story Become an Adweek+ Subscriber
Already a member? Sign in