🔗 The Art and Science of Image Discovery at Netflix

This is a fascinating technical deep-dive on how Netflix identifies which still image frames to use to best represent each title:

A single season of an average TV show (about 10 episodes) contains nearly 9 million total frames. Asking creative editors to efficiently sift through that many frames of video to identify one frame that will capture an audience’s attention is tedious and ineffective. We set out to build a tool that quickly and effectively identifies which frames are the best moments to represent a title on the Netflix service.

The B-Sides @RianVDM