The video embeddings in the paper are learned purely based on observing what users co-watch in sessions. In this sense, they can be thought of as latent factors in more traditional collaborative filtering approaches. When we inspect them, nearby vectors have a surprising amount of semantic similarity.
Features about the videos such as titles and tags, as well as features derived from audio and video, are introduced in the ranking phase.
Features about the videos such as titles and tags, as well as features derived from audio and video, are introduced in the ranking phase.