公开(公告)号：US11250252B2

公开(公告)日：2022-02-15

申请号：US16701586

申请日：2019-12-03

Applicant: ADOBE INC.

Inventor： Christopher Alan Tensmeyer ,  Rajiv Jain ,  Curtis Michael Wigington ,  Brian Lynn Price ,  Brian Lafayette Davis

IPC: G06K9/00 ,  G06F3/0488 ,  G06N3/04 ,  G06K9/22 ,  G06N3/08

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.

公开(公告)号：US20210334664A1

公开(公告)日：2021-10-28

申请号：US16865605

申请日：2020-05-04

Applicant: Adobe Inc.

Inventor： Kai Li ,  Christopher Alan Tensmeyer ,  Curtis Michael Wigington ,  Handong Zhao ,  Nikolaos Barmpalios ,  Tong Sun ,  Varun Manjunatha ,  Vlad Ion Morariu

IPC: G06N3/08 ,  G06N20/10 ,  G06K9/62 ,  G06K9/00 ,  G06F17/18

Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

公开(公告)号：US20240135165A1

公开(公告)日：2024-04-25

申请号：US18047335

申请日：2022-10-18

Applicant: ADOBE INC.

Inventor： Varun Manjunatha ,  Sarthak Jain ,  Rajiv Bhawanji Jain ,  Ani Nenkova Nenkova ,  Christopher Alan Tensmeyer ,  Franck Dernoncourt ,  Quan Hung Tran ,  Ruchi Deshpande

IPC: G06N3/08 ,  G06F40/295

CPC classification number: G06N3/08 ,  G06F40/295

Abstract: One aspect of systems and methods for data correction includes identifying a false label from among predicted labels corresponding to different parts of an input sample, wherein the predicted labels are generated by a neural network trained based on a training set comprising training samples and training labels corresponding to parts of the training samples; computing an influence of each of the training labels on the false label by approximating a change in a conditional loss for the neural network corresponding to each of the training labels; identifying a part of a training sample of the training samples and a corresponding source label from among the training labels based on the computed influence; and modifying the training set based on the identified part of the training sample and the corresponding source label to obtain a corrected training set.

公开(公告)号：US20230161943A1

公开(公告)日：2023-05-25

申请号：US17535067

申请日：2021-11-24

Applicant: Adobe Inc.

Inventor： Vlad Ion Morariu ,  Yuexi Chen ,  Christopher Alan Tensmeyer ,  Zhicheng Liu ,  Lars Niklas Emanuel Elmqvist

IPC: G06F40/106 ,  G06F40/166 ,  G06F40/117

CPC classification number: G06F40/106 ,  G06F40/166 ,  G06F40/117

Abstract: Systems and techniques for generating responsive documents are described. Digital content is organized into a structure that defines how content is presented when a document is displayed by a computing device. To generate the responsive document, relationships are defined among different digital content objects, such as groups of content objects to be presented together and content objects that are to be presented as alternatives of one another. Responsive patterns are assigned to grouped content objects, where each responsive pattern defines different layout configurations for displaying grouped content objects based on computing device display characteristics. In some implementations, multiple responsive patterns are assigned to a single content group and individual responsive patterns are associated with activation ranges for display characteristics that activate the responsive pattern. For groups of digital content objects that are assigned multiple responsive patterns, responsive patterns are prioritized to create a hierarchy dictating display of the responsive document.

公开(公告)号：US20220391768A1

公开(公告)日：2022-12-08

申请号：US17883811

申请日：2022-08-09

Applicant: Adobe Inc.

Inventor： Kai Li ,  Christopher Alan Tensmeyer ,  Curtis Michael Wigington ,  Handong Zhao ,  Nikolaos Barmpalios ,  Tong Sun ,  Varun Manjunatha ,  Vlad Ion Morariu

IPC: G06N20/00 ,  G06N3/04

Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

公开(公告)号：US20220148326A1

公开(公告)日：2022-05-12

申请号：US17648718

申请日：2022-01-24

Applicant: Adobe Inc.

Inventor： Christopher Alan Tensmeyer ,  Rajiv Jain ,  Curtis Michael Wigington ,  Brian Lynn Price ,  Brian Lafayette Davis

IPC: G06V30/32 ,  G06F3/04883 ,  G06N3/04 ,  G06N3/08 ,  G06V30/228 ,  G06V30/226

Abstract: Techniques are provided for generating a digital image of simulated handwriting using an encoder-decoder neural network trained on images of natural handwriting samples. The simulated handwriting image can be generated based on a style of a handwriting sample and a variable length coded text input. The style represents visually distinctive characteristics of the handwriting sample, such as the shape, size, slope, and spacing of the letters, characters, or other markings in the handwriting sample. The resulting simulated handwriting image can include the text input rendered in the style of the handwriting sample. The distinctive visual appearance of the letters or words in the simulated handwriting image mimics the visual appearance of the letters or words in the handwriting sample image, whether the letters or words in the simulated handwriting image are the same as in the handwriting sample image or different from those in the handwriting sample image.