-
-
公开(公告)号：US12119028B2
公开(公告)日：2024-10-15
申请号：US17967364
申请日：2022-10-17
Applicant: Adobe Inc.
Inventor： Xue Bai , Justin Jonathan Salamon , Aseem Omprakash Agarwala , Hijung Shin , Haoran Cai , Joel Richard Brandt , Lubomira Assenova Dontcheva , Cristin Ailidh Fraser
IPC: G11B27/036 , G06F40/166 , G10L15/26 , G10L25/57 , G11B27/34 , G06F3/0482 , G06F3/04845 , G06F3/0485
CPC classification number: G11B27/036 , G06F40/166 , G10L15/26 , G10L25/57 , G11B27/34 , G06F3/0482 , G06F3/04845 , G06F3/0485
Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for identifying candidate boundaries for video segments, video segment selection using those boundaries, and text-based video editing of video segments selected via transcript interactions. In an example implementation, boundaries of detected sentences and words are extracted from a transcript, the boundaries are retimed into an adjacent speech gap to a location where voice or audio activity is a minimum, and the resulting boundaries are stored as candidate boundaries for video segments. As such, a transcript interface presents the transcript, interprets input selecting transcript text as an instruction to select a video segment with corresponding boundaries selected from the candidate boundaries, and interprets commands that are traditionally thought of as text-based operations (e.g., cut, copy, paste) as an instruction to perform a corresponding video editing operation using the selected video segment.
-
公开(公告)号：US20200051302A1
公开(公告)日：2020-02-13
申请号：US16057668
申请日：2018-08-07
Applicant: ADOBE INC.
Inventor： Hariharan Subramonyam , Eytan Adar , Lubomira Assenova Dontcheva , Wilmot Wei-Mau Li
Abstract: Techniques described herein relate to a streamlined animation production workflow that integrates script drafting, performance, and editing. A script including animation events is parsed to encode the animation events into nodes of a story model. The animation events are automatically triggered by a performance as a playhead advances through the story model and identifies active node(s). A command interface accepts various commands that allow a performer to act as a director by controlling recording and playback. Recording binds a generated animation event to each active node. Playback triggers generated animation events for active nodes. An animated movie is assembled from the generated animation events in the story model. The animated movie can be presented as a live preview to provide feedback to the performer, and a teleprompter interface can guide a performer by presenting and advancing the script to follow the performance.
-
公开(公告)号：US10546409B1
公开(公告)日：2020-01-28
申请号：US16057668
申请日：2018-08-07
Applicant: ADOBE INC.
Inventor： Hariharan Subramonyam , Eytan Adar , Lubomira Assenova Dontcheva , Wilmot Wei-Mau Li
Abstract: Techniques described herein relate to a streamlined animation production workflow that integrates script drafting, performance, and editing. A script including animation events is parsed to encode the animation events into nodes of a story model. The animation events are automatically triggered by a performance as a playhead advances through the story model and identifies active node(s). A command interface accepts various commands that allow a performer to act as a director by controlling recording and playback. Recording binds a generated animation event to each active node. Playback triggers generated animation events for active nodes. An animated movie is assembled from the generated animation events in the story model. The animated movie can be presented as a live preview to provide feedback to the performer, and a teleprompter interface can guide a performer by presenting and advancing the script to follow the performance.
-
-
-
Search Results
14
records
(took 0.014 seconds)
