{"id":8841,"date":"2019-06-10T10:29:01","date_gmt":"2019-06-10T17:29:01","guid":{"rendered":"http:\/\/jnack.com\/blog\/?p=8841"},"modified":"2019-06-10T12:09:33","modified_gmt":"2019-06-10T19:09:33","slug":"adobe-co-enable-video-manipulation-through-typing","status":"publish","type":"post","link":"http:\/\/jnack.com\/blog\/2019\/06\/10\/adobe-co-enable-video-manipulation-through-typing\/","title":{"rendered":"Adobe &#038; co. enable video manipulation through typing"},"content":{"rendered":"<p>There\u2019s no way <a href=\"https:\/\/www.ohadf.com\/projects\/text-based-editing\/\">this<\/a> can end badly\u2014no way.<\/p>\n<p><iframe loading=\"lazy\" title=\"Text-based Editing of Talking-head Video (SIGGRAPH 2019)\" width=\"604\" height=\"453\" src=\"https:\/\/www.youtube.com\/embed\/0ybLCfVeFL4?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>The Verge <a href=\"https:\/\/www.theverge.com\/2019\/6\/10\/18659432\/deepfake-ai-fakes-tech-edit-video-by-typing-new-words\">writes<\/a>,<\/p>\n<blockquote><p>When someone edits a text transcript of the video, the software combines all this collected data \u2014 the phonemes, visemes, and 3D face model \u2014 to construct new footage that matches the text input. This is then pasted onto the source video to create the final result.<\/p>\n<p>In tests in which the fake videos were shown to a group of 138 volunteers, some 60 percent of participants though the edits were real. That may sound quite low, but only 80 percent of that same group thought the original, unedited footage was also legitimate.<\/p><\/blockquote>\n<p><img decoding=\"async\" loading=\"lazy\" title=\"NewImage.png\" src=\"http:\/\/jnack.com\/blog\/wp-content\/uploads\/2019\/06\/NewImage-4.png\" alt=\"NewImage\" width=\"600\" height=\"198\" border=\"0\"><\/p>\n<p>See <a href=\"http:\/\/jnack.com\/blog\/2017\/06\/27\/a-closer-look-at-adobes-audio-photoshopping\/\">previous<\/a>: &#8220;Audio Photoshopping&#8221; using Adobe VoCo:<br \/>\n<iframe loading=\"lazy\" title=\"VoCo: Text-based Insertion and Replacement in Audio Narration\" width=\"604\" height=\"340\" src=\"https:\/\/www.youtube.com\/embed\/RB7upq8nzIU?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen><\/iframe><\/p>\n<p>[<a href=\"https:\/\/youtu.be\/0ybLCfVeFL4\">YouTube 1<\/a> &amp; <a href=\"https:\/\/youtu.be\/RB7upq8nzIU\">2<\/a>]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>There\u2019s no way this can end badly\u2014no way. The Verge writes, When someone edits a text transcript of the video, the software combines all this collected data \u2014 the phonemes, visemes, and 3D face model \u2014 to construct new footage that matches the text input. This is then pasted onto the source video to create [&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\/8841"}],"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=8841"}],"version-history":[{"count":3,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/8841\/revisions"}],"predecessor-version":[{"id":8845,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/posts\/8841\/revisions\/8845"}],"wp:attachment":[{"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/media?parent=8841"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/categories?post=8841"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/jnack.com\/blog\/wp-json\/wp\/v2\/tags?post=8841"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}