This is great stuff.<p>Given the insane progress in speech\voice recognition in audio in the last 2-3 years, I have been wondering how soon we are going to see the same accuracy levels for object rec in video. Lots and lots of new apps on the horizon...
i didn't see a link to the github on the site, so for those wondering: <a href="https://github.com/cvondrick/vatic/" rel="nofollow">https://github.com/cvondrick/vatic/</a>.