A web service that lets you submit videos in various formats and perform visual analysis: shot & scene segmentation, and visual concept detection; and then perform concept-based search within the collection of shots and scenes.

The newly-released v5.0 of the service supports the YouTube-8M concepts with the help of a new deep learning architecture; a previous version v4.0 learning architecture; a previous version v4.0 that supports a different concept set using an older deep learning approach is also available.