News for hackers. Stuff that matters.
Re:Ask HN: How is automatic video tagging is done based on i... by Rust on Sunday May 27, 2012 @05:20PM (#4031041)
One way might be to run the audio stream through a speech-to-text engine and parse the resulting transcript.

A video recognition system could also be used to identify faces, landmarks and common objects.

There are no comments on this comment yet.