-
公开(公告)号：US11972757B2
公开(公告)日：2024-04-30
申请号：US18149286
申请日：2023-01-03
Applicant: Adobe Inc.
Inventor： Frieder Ludwig Anton Ganz , Walter Wei-Tuh Chang
IPC: G10L15/22 , G06F3/0481 , G06F3/16 , G06T7/00 , G10L15/18
CPC classification number: G10L15/1815 , G06F3/0481 , G06F3/167 , G06T7/0002 , G10L15/22 , G06T2207/10004 , G06T2207/30168 , G10L2015/223
Abstract: Conversational image editing and enhancement techniques are described. For example, an indication of a digital image is received from a user. Aesthetic attribute scores for multiple aesthetic attributes of the image are generated. A computing device then conducts a natural language conversation with the user to edit the digital image. The computing device receives inputs from the user to refine the digital image as the natural language conversation progresses. The computing device generates natural language suggestions to edit the digital image based on the aesthetic attribute scores as part of the natural language conversation. The computing device provides feedback to the user that includes edits to the digital image based on the series of inputs. The computing device also includes as feedback natural language outputs indicating options for additional edits to the digital image based on the series of inputs and the previous edits to the digital image.
-
公开(公告)号：US10769495B2
公开(公告)日：2020-09-08
申请号：US16052246
申请日：2018-08-01
Applicant: Adobe Inc.
Inventor： Trung Huu Bui , Zhe Lin , Walter Wei-Tuh Chang , Nham Van Le , Franck Dernoncourt
IPC: G06K9/62 , G06F3/16 , G06F3/0488 , G10L15/06 , G06F9/451 , G06F3/0482 , G06F16/54 , G06N3/08 , G06N20/00 , G06F3/0484
Abstract: In implementations of collecting multimodal image editing requests (IERs), a user interface is generated that exposes an image pair including a first image and a second image including at least one edit to the first image. A user simultaneously speaks a voice command and performs a user gesture that describe an edit of the first image used to generate the second image. The user gesture and the voice command are simultaneously recorded and synchronized with timestamps. The voice command is played back, and the user transcribes their voice command based on the play back, creating an exact transcription of their voice command. Audio samples of the voice command with respective timestamps, coordinates of the user gesture with respective timestamps, and a transcription are packaged as a structured data object for use as training data to train a neural network to recognize multimodal IERs in an image editing application.
-
公开(公告)号：US10713519B2
公开(公告)日：2020-07-14
申请号：US15630779
申请日：2017-06-22
Applicant: ADOBE INC.
Inventor： Trung Huu Bui , Hung Hai Bui , Shawn Alan Gaither , Walter Wei-Tuh Chang , Michael Frank Kraley , Pranjal Daga
Abstract: The present invention is directed towards providing automated workflows for the identification of a reading order from text segments extracted from a document. Ordering the text segments is based on trained natural language models. In some embodiments, the workflows are enabled to perform a method for identifying a sequence associated with a portable document. The methods includes iteratively generating a probabilistic language model, receiving the portable document, and selectively extracting features (such as but not limited to text segments) from the document. The method may generate pairs of features (or feature pair from the extracted features). The method may further generate a score for each of the pairs based on the probabilistic language model and determine an order to features based on the scores. The method may provide the extracted features in the determined order.
-
公开(公告)号：US10606959B2
公开(公告)日：2020-03-31
申请号：US16196859
申请日：2018-11-20
Applicant: Adobe Inc.
Inventor： Carl Iwan Dockhorn , Sean Michael Fitzgerald , Ragunandan Rao Malangully , Laurie Marie Byrum , Jason Guthrie Waters , Frederic Claude Thevenet , Walter Wei-Tuh Chang
Abstract: Highlighting key portions of text within a document is described. A document having text is obtained, and key portions of the document are determined using summarization techniques. Key portion data indicative of the key portions is generated and maintained for output to generate a highlighted document in which highlight overlays are displayed over or proximate the determined key portions of the text within the document. In one or more implementations, reader interactions with the highlighted document are monitored to generate reader feedback data. The reader feedback data may then be combined with the output of the summarization techniques in order to adjust the determined key portions. In some cases, the reader feedback data may also be used to improve the summarization techniques.
-
公开(公告)号：US20200042286A1
公开(公告)日：2020-02-06
申请号：US16052246
申请日：2018-08-01
Applicant: Adobe Inc.
Inventor： Trung Huu Bui , Zhe Lin , Walter Wei-Tuh Chang , Nham Van Le , Franck Dernoncourt
IPC: G06F3/16 , G10L15/26 , G06F3/0488 , G06F3/0482 , G10L15/06 , G06F17/30 , G06F9/451
Abstract: In implementations of collecting multimodal image editing requests (IERs), a user interface is generated that exposes an image pair including a first image and a second image including at least one edit to the first image. A user simultaneously speaks a voice command and performs a user gesture that describe an edit of the first image used to generate the second image. The user gesture and the voice command are simultaneously recorded and synchronized with timestamps. The voice command is played back, and the user transcribes their voice command based on the play back, creating an exact transcription of their voice command. Audio samples of the voice command with respective timestamps, coordinates of the user gesture with respective timestamps, and a transcription are packaged as a structured data object for use as training data to train a neural network to recognize multimodal IERs in an image editing application.
-
Patent Agency Ranking
公开(公告)号：US10389804B2
公开(公告)日：2019-08-20
申请号：US14938660
申请日：2015-11-11
Applicant: Adobe Inc.
Inventor： Zeke Koch , Gavin Stuart Peter Miller , Jonathan W. Brandt , Nathan A. Carr , Radomir Mech , Walter Wei-Tuh Chang , Scott D. Cohen , Hailin Jin
Abstract: Content creation and sharing integration techniques and systems are described. In one or more implementations, techniques are described in which modifiable versions of content (e.g., images) are created and shared via a content sharing service such that image creation functionality used to create the images is preserved to permit continued creation using this functionality. In one or more additional implementations, image creation functionality employed by a creative professional to create content is leveraged to locate similar images from a content sharing service.
-
公开(公告)号：US10249061B2
公开(公告)日：2019-04-02
申请号：US14938628
申请日：2015-11-11
Applicant: Adobe Inc.
Inventor： Zeke Koch , Gavin Stuart Peter Miller , Jonathan W. Brandt , Nathan A. Carr , Radomir Mech , Walter Wei-Tuh Chang , Scott D. Cohen , Hailin Jin
IPC: G06F3/0484 , G06F17/27 , G06T11/00 , G06F16/583 , G06F16/58 , G06F16/9535 , G06T11/60 , G06F16/50
Abstract: Content creation and sharing integration techniques and systems are described. In one or more implementations, techniques are described in which modifiable versions of content (e.g., images) are created and shared via a content sharing service such that image creation functionality used to create the images is preserved to permit continued creation using this functionality. In one or more additional implementations, image creation functionality employed by a creative professional to create content is leveraged to locate similar images from a content sharing service.
-
公开(公告)号：US10235464B2
公开(公告)日：2019-03-19
申请号：US14703889
申请日：2015-05-05
Applicant: Adobe Inc.
Inventor： Anmol Dhawan , Walter Wei-Tuh Chang , Ashish Duggal , Sachin Soni
Abstract: A method for recommending hashtags includes determining keywords from a post planned for publishing by a publisher. An input criteria comprising at least one of age group, geographical location, date range, or a keyword is received. Previous posts associated with the keywords and satisfying the input criteria are obtained. The previous posts are categorized into one or more categories based on sentiment of each post and for each category hashtags used in the obtained previous posts in that category are determined. The hashtags are ranked based on predefined criteria comprising at least one of frequency of appearance of respective hashtag in posts, number of likes or shares or retweets of post comprising respective hashtag, number of followers of person who used respective hashtag, or sentiment of post comprising respective hashtag. The hashtags are then recommended, based on ranking, to the publisher for use with the post planned for publishing.
-
公开(公告)号：US11574630B2
公开(公告)日：2023-02-07
申请号：US17015765
申请日：2020-09-09
Applicant: Adobe Inc.
Inventor： Frieder Ludwig Anton Ganz , Walter Wei-Tuh Chang
IPC: G10L15/22 , G10L15/18 , G06T7/00 , G06F3/16 , G06F3/0481
Abstract: Conversational image editing and enhancement techniques are described. For example, an indication of a digital image is received from a user. Aesthetic attribute scores for multiple aesthetic attributes of the image are generated. A computing device then conducts a natural language conversation with the user to edit the digital image. The computing device receives inputs from the user to refine the digital image as the natural language conversation progresses. The computing device generates natural language suggestions to edit the digital image based on the aesthetic attribute scores as part of the natural language conversation. The computing device provides feedback to the user that includes edits to the digital image based on the series of inputs. The computing device also includes as feedback natural language outputs indicating options for additional edits to the digital image based on the series of inputs and the previous edits to the digital image.
-
20.发明申请公开(公告)号：US20200320329A1
公开(公告)日：2020-10-08
申请号：US16904881
申请日：2020-06-18
Applicant: ADOBE INC.
Inventor： Trung Huu Bui , Hung Hai Bui , Shawn Alan Gaither , Walter Wei-Tuh Chang , Michael Frank Kraley , Pranjal Daga
Abstract: The present invention is directed towards providing automated workflows for the identification of a reading order from text segments extracted from a document. Ordering the text segments is based on trained natural language models. In some embodiments, the workflows are enabled to perform a method for identifying a sequence associated with a portable document. The methods includes iteratively generating a probabilistic language model, receiving the portable document, and selectively extracting features (such as but not limited to text segments) from the document. The method may generate pairs of features (or feature pair from the extracted features). The method may further generate a score for each of the pairs based on the probabilistic language model and determine an order to features based on the scores. The method may provide the extracted features in the determined order.
-
-
-
-
-
-
-
-
-
Search Results
26
records
(took 0.019 seconds)
