{"id":5830,"date":"2017-08-23T07:54:58","date_gmt":"2017-08-23T14:54:58","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=5830"},"modified":"2017-08-22T13:55:09","modified_gmt":"2017-08-22T20:55:09","slug":"adobe-stanford-collaborate-to-automate-video-editing","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2017\/08\/23\/adobe-stanford-collaborate-to-automate-video-editing\/","title":{"rendered":"Adobe &#038; Stanford collaborate to automate video editing"},"content":{"rendered":"<p>I\u2019ve <a href=\"http:\/\/blogs.adobe.com\/jnack\/2013\/10\/automatic-videos-do-you-care.html\">long<\/a> been skeptical of automated video editing. As I <a href=\"http:\/\/jnack.com\/blog\/2017\/05\/31\/flo-rider-intelligent-automatic-video-creation\/\">noted<\/a> in May,<\/p>\n<blockquote>\n<p>My Emmy-winning colleague Bill Hensler, who used to head up video engineering at Adobe, said he\u2019d been pitched similar tech since the early 90\u2019s and always said, \u201cSure, just show me a system that can match a shot of a guy entering a room with another shot of the same thing from a different angle\u2014then we\u2019ll talk.\u201d As far as I know, we\u2019re still waiting.<\/p>\n<\/blockquote>\n<p>Now, however, some researchers at Adobe &amp; Stanford are narrowing the problem, focusing just on saving editors time via &#8220;<a href=\"https:\/\/graphics.stanford.edu\/papers\/roughcut\/\">Computational Video Editing for Dialogue-Driven Scenes<\/a>\u201d:<\/p>\n<blockquote>\n<p>Given a script and multiple video recordings, or takes, of a dialogue-driven scene as input (left), our computational video editing system automatically selects the most appropriate clip from one of the takes for each line of dialogue in the script based on a set of user-specified film-editing idioms (right).<\/p>\n<\/blockquote>\n<p>Check out the short demo (where the cool stuff starts ~2 minutes in):<\/p>\n<p><iframe loading=\"lazy\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/tF43Zqoue20?feature=oembed\" frameborder=\"0\" allow=\"autoplay; encrypted-media\" allowfullscreen><\/iframe><\/p>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2017\/08\/NewImage-28.png\" alt=\"NewImage\" width=\"600\" height=\"187\" border=\"0\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>I\u2019ve long been skeptical of automated video editing. As I noted in May, My Emmy-winning colleague Bill Hensler, who used to head up video engineering at Adobe, said he\u2019d been pitched similar tech since the early 90\u2019s and always said, \u201cSure, just show me a system that can match a shot of a guy entering [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[8],"tags":[],"_links":{"self":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/5830"}],"collection":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/comments?post=5830"}],"version-history":[{"count":2,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/5830\/revisions"}],"predecessor-version":[{"id":5836,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/5830\/revisions\/5836"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=5830"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=5830"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=5830"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}