-
11.发明授权公开(公告)号：US12147771B2
公开(公告)日：2024-11-19
申请号：US17361878
申请日：2021-06-29
Applicant: ADOBE INC.
Inventor： Sangwoo Cho , Franck Dernoncourt , Timothy Jeewun Ganter , Trung Huu Bui , Nedim Lipka , Varun Manjunatha , Walter Chang , Hailin Jin , Jonathan Brandt
IPC: G06F40/35 , G06F40/279
Abstract: System and methods for a text summarization system are described. In one example, a text summarization system receives an input utterance and determines whether the utterance should be included in a summary of the text. The text summarization system includes an embedding network, a convolution network, an encoding component, and a summary component. The embedding network generates a semantic embedding of an utterance. The convolution network generates a plurality of feature vectors based on the semantic embedding. The encoding component identifies a plurality of latent codes respectively corresponding to the plurality of feature vectors. The summary component identifies a prominent code among the latent codes and to select the utterance as a summary utterance based on the prominent code.
-
公开(公告)号：US20240135613A1
公开(公告)日：2024-04-25
申请号：US18320664
申请日：2023-05-19
Applicant: Adobe Inc.
Inventor： Zhihong Ding , Scott Cohen , Matthew Joss , Jianming Zhang , Darshan Prasad , Celso Gomes , Jonathan Brandt
CPC classification number: G06T11/60 , G06F3/04842 , G06T3/40 , G06T5/005 , G06T7/50 , G06V10/761 , G06T2207/20084
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that implement perspective-aware object move operations for digital image editing. For instance, in some embodiments, the disclosed systems determine a vanishing point associated with a digital image portraying an object. Additionally, the disclosed systems detect one or more user interactions for moving the object within the digital image. Based on moving the object with respect to the vanishing point, the disclosed systems perform a perspective-based resizing of the object within the digital image.
-
公开(公告)号：US11636270B2
公开(公告)日：2023-04-25
申请号：US16775697
申请日：2020-01-29
Applicant: ADOBE INC.
Inventor： Zhe Lin , Walter W. Chang , Scott Cohen , Khoi Viet Pham , Jonathan Brandt , Franck Dernoncourt
IPC: G06F40/30 , G06F16/532 , G06F16/55 , G06F40/205 , G06F40/295 , G06N5/02 , G06N5/04 , G06N20/00 , G06V10/40 , G06V30/10
Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for parsing a given input referring expression into a parse structure and generating a semantic computation graph to identify semantic relationships among and between objects. At a high level, when embodiments of the preset invention receive a referring expression, a parse tree is created and mapped into a hierarchical subject, predicate, object graph structure that labeled noun objects in the referring expression, the attributes of the labeled noun objects, and predicate relationships (e.g., verb actions or spatial propositions) between the labeled objects. Embodiments of the present invention then transform the subject, predicate, object graph structure into a semantic computation graph that may be recursively traversed and interpreted to determine how noun objects, their attributes and modifiers, and interrelationships are provided to downstream image editing, searching, or caption indexing tasks.
-
14.发明申请公开(公告)号：US20220414338A1
公开(公告)日：2022-12-29
申请号：US17361878
申请日：2021-06-29
Applicant: ADOBE INC.
Inventor： SANGWOO CHO , Franck Dernoncourt , Timothy Jeewun Ganter , Trung Huu Bui , Nedim Lipka , Varun Manjunatha , Walter Chang , Hailin Jin , Jonathan Brandt
IPC: G06F40/35 , G06F40/279
Abstract: System and methods for a text summarization system are described. In one example, a text summarization system receives an input utterance and determines whether the utterance should be included in a summary of the text. The text summarization system includes an embedding network, a convolution network, an encoding component, and a summary component. The embedding network generates a semantic embedding of an utterance. The convolution network generates a plurality of feature vectors based on the semantic embedding. The encoding component identifies a plurality of latent codes respectively corresponding to the plurality of feature vectors. The summary component identifies a prominent code among the latent codes and to select the utterance as a summary utterance based on the prominent code.
-
公开(公告)号：US20210232770A1
公开(公告)日：2021-07-29
申请号：US16775697
申请日：2020-01-29
Applicant: ADOBE INC.
Inventor： Zhe Lin , Walter W. Chang , Scott Cohen , Khoi Viet Pham , Jonathan Brandt , Franck Dernoncourt
IPC: G06F40/30 , G06F16/532 , G06F16/55 , G06N5/02 , G06N20/00 , G06N5/04 , G06K9/46 , G06F40/205 , G06F40/295
Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for parsing a given input referring expression into a parse structure and generating a semantic computation graph to identify semantic relationships among and between objects. At a high level, when embodiments of the preset invention receive a referring expression, a parse tree is created and mapped into a hierarchical subject, predicate, object graph structure that labeled noun objects in the referring expression, the attributes of the labeled noun objects, and predicate relationships (e.g., verb actions or spatial propositions) between the labeled objects. Embodiments of the present invention then transform the subject, predicate, object graph structure into a semantic computation graph that may be recursively traversed and interpreted to determine how noun objects, their attributes and modifiers, and interrelationships are provided to downstream image editing, searching, or caption indexing tasks.
-
Patent Agency Ranking
公开(公告)号：US20210056408A1
公开(公告)日：2021-02-25
申请号：US16549072
申请日：2019-08-23
Applicant: Adobe Inc.
Inventor： Jonathan Brandt , Chen Fang , Byungmoon Kim , Biao Jia
Abstract: The technology described herein is directed to a reinforcement learning based framework for training a natural media agent to learn a rendering policy without human supervision or labeled datasets. The reinforcement learning based framework feeds the natural media agent a training dataset to implicitly learn the rendering policy by exploring a canvas and minimizing a loss function. Once trained, the natural media agent can be applied to any reference image to generate a series (or sequence) of continuous-valued primitive graphic actions, e.g., sequence of painting strokes, that when rendered by a synthetic rendering environment on a canvas, reproduce an identical or transformed version of the reference image subject to limitations of an action space and the learned rendering policy.
-
公开(公告)号：US20200004873A1
公开(公告)日：2020-01-02
申请号：US16020328
申请日：2018-06-27
Applicant: Adobe Inc.
Inventor： Walter W. Chang , Jonathan Brandt , Doo Soon Kim
IPC: G06F17/30
Abstract: Techniques of directing a user to content based on a semantic interpretation of a query input by the user involves generating links to specific content in a collection of documents in response to user string query, the links being generated based on an answer suggestion lookahead index. The answer suggestion lookahead index references a mapping between a plurality of groups of semantically equivalent terms and a respective link to specific content of the collection of documents. These techniques are useful for the generalized task of natural language question answering.
-
公开(公告)号：US11152032B2
公开(公告)日：2021-10-19
申请号：US16395041
申请日：2019-04-25
Applicant: Adobe Inc.
Inventor： Zhihong Ding , Zhe Lin , Xiaohui Shen , Michael Kaplan , Jonathan Brandt
Abstract: The present disclosure is directed toward systems and methods for tracking objects in videos. For example, one or more embodiments described herein utilize various tracking methods in combination with an image search index made up of still video frames indexed from a video. One or more embodiments described herein utilize a backward and forward tracking method that is anchored by one or more key frames in order to accurately track an object through the frames of a video, even when the video is long and may include challenging conditions.
-
公开(公告)号：US11120059B2
公开(公告)日：2021-09-14
申请号：US16020328
申请日：2018-06-27
Applicant: Adobe Inc.
Inventor： Walter W. Chang , Jonathan Brandt , Doo Soon Kim
IPC: G06F16/00 , G06F16/332 , G06F16/93 , G06F16/33 , G06F16/338 , G06F16/31
Abstract: Techniques of directing a user to content based on a semantic interpretation of a query input by the user involves generating links to specific content in a collection of documents in response to user string query, the links being generated based on an answer suggestion lookahead index. The answer suggestion lookahead index references a mapping between a plurality of groups of semantically equivalent terms and a respective link to specific content of the collection of documents. These techniques are useful for the generalized task of natural language question answering.
-
20.发明授权公开(公告)号：US10430689B2
公开(公告)日：2019-10-01
申请号：US15680282
申请日：2017-08-18
Applicant: Adobe Inc.
Inventor： Zhe Lin , Stefan Guggisberg , Jonathan Brandt , Michael Marth
Abstract: This disclosure relates to training a classifier algorithm that can be used for automatically selecting tags to be applied to a received image. For example, a computing device can group training images together based on the training images having similar tags. The computing device trains a classifier algorithm to identify the training images as semantically similar to one another based on the training images being grouped together. The trained classifier algorithm is used to determine that an input image is semantically similar to an example tagged image. A tag is generated for the input image using tag content from the example tagged image based on determining that the input image is semantically similar to the tagged image.
-
-
-
-
-
-
-
-
-
Search Results
24
records
(took 0.034 seconds)
