X

Asterpix to take the work out of tagging videos

Take the work out of tagging with Asterpix's upcoming tagging bot.

Josh Lowensohn Former Senior Writer
Josh Lowensohn joined CNET in 2006 and now covers Apple. Before that, Josh wrote about everything from new Web start-ups, to remote-controlled robots that watch your house. Prior to joining CNET, Josh covered breaking video game news, as well as reviewing game software. His current console favorite is the Xbox 360.
Josh Lowensohn
2 min read

Asterpix, a video tagging service we looked at late last year is launching some exciting new technology later this month. It's a new automated tagging service that will go through any video you plug in and use its recognition algorithms to tag and link whatever's in your video to informational resources about it on the Web.

In its current state, the service lets you accomplish a similar feat, adding text and URL links to various objects--although the process is manual. On the 17th, users will simply be able to run videos from many major hosting services through Asterpix's tagging bot and have tags created automatically before adding their own.

Find out more about video clips using Asterpix's upcoming auto-tagging service. CNET Networks

The Asterbot has already been doing this to several thousand videos a day and making the entire index of robot-created tags searchable alongside those made by humans. Video tags can pull up information from all over the Web. In one case I was watching a clip from Cheech and Chong, and there was a timed tag that had automatically been inserted with an anecdote about a certain part of the scene. That anecdote had come from IMDB, although the creators tell me information can come from less well-known sources as long as it's been indexed in major search engines.

The actual process of machine-tagging involves pulling in imaging data from the video clip and matching it up to whatever text was included by the video's creator. Nat Kausik, CEO of Asterpix tells me the process is a little similar to Google's search algorithm in creating relevancy based on what bits of parts of the video get the most screen time. For example, in a video of a someone walking through a grocery store there would be a wealth of information about other products and people, but if you're focused on that one person for the majority of the clip the engine will pick on it and react accordingly.

While there are no ads inserted into Asterpix-tagged videos yet, Kasuik says it's clearly a direction the company is going in. Contextual video advertising is already in action from Google, and is under development from over a dozen other companies. In the meantime, Asterpix's next move is a widget for video publishers that will do some of the tagging at the point of upload.