Hacker News new | past | comments | ask | show | jobs | submit login
How YouTube thinks about copyright [video] (ted.com)
4 points by jparise on June 18, 2010 | hide | past | favorite | 1 comment



In summary, YouTube's "content ID" system attempts to match uploaded videos against a large database of registered copyrighted content. If it finds a match, it applies a policy that was defined by the copyright holder.

The system handles the full volume of uploaded video content (equivalent to "100 years of video per day"). Even more impressive is the fact that it can successfully identify multiple copyrighted portions of a video (think mashups).




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: