MIT Team Creates Video From Still Photo

November 30, 2016

The team started by setting up an algorithm to “watch” 2 million random videos—about two years worth—to learn scene dynamics, and use that knowledge to generate video.

“We use a large amount of unlabeled video to train our model. We downloaded over 2 million videos from Flickr by querying for popular Flickr tags as well as querying for common English words,” they said.

Read more at: http://www.tvtechnology.com/news/0002/mit-team-creates-video-from-still-photo/279915


Get the Media Source Newsletter on your smartphone or tablet now!

iphone
Android

 


Latest News

Family Radio selling stations, moving headquarters to Nashville

Family Radio, the theologically conservative radio station...

Posted

Full-Power Radio Fears New Interference Problems From Proposed LPFM Changes

Broadcasters are feeling both concern and hope for potential opportunities over a proposal the Federal Communications Commission is considering...

Posted

FCC To Hold Symposium on Radio and TV Industry

The FCC announced on Friday that it will be hosting a symposium on the state of the broadcast industry on November 21.

Posted

Sen. Graham Proposes STELAR Sunset Transition Plan

Sen. Lindsey Graham (R-S.C.), chairman of the Senate Judiciary Committee, which shares jurisdiction over the issue with Commerce...

Posted

More News

NEWSROOM

Headlines