Disney makes its archive accessible using deep learning built on AWS
From over a century of drawings and concept work to live action and animated video content, Disney wants to not only preserve its archive, but also make it easily searchable for its writers and illustrators who may need it for reference or inspiration.
The key to surfacing the right content at the right time is metadata: information about the stories, scenes, and characters in Disney’s shows and movies. However, appropriately tagging all of this content with the right metadata to allow it to be sorted properly presents several challenges including metadata standardization and how cost prohibitive it can be to do manually.
With the help of AWS, Disney’s Direct-to-Consumer & International (DTCI) Technology team is building machine learning and deep learning tools to automate metadata tagging and make the archiving process more efficient.