公开(公告)号：US12008698B2

公开(公告)日：2024-06-11

申请号：US18117155

申请日：2023-03-03

Applicant: Adobe Inc.

Inventor： Midhun Harikumar ,  Pranav Aggarwal ,  Baldo Faieta ,  Ajinkya Kale ,  Zhe Lin

IPC: G06T11/60 ,  G06T7/11 ,  G06T7/162

CPC classification number: G06T11/60 ,  G06T7/11 ,  G06T7/162 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, using a model, a learned image representation of a target image. The operations further include generating, using a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image based on the convolving of the learned image representation of the target image with the text embedding.

公开(公告)号：US11687714B2

公开(公告)日：2023-06-27

申请号：US16998730

申请日：2020-08-20

Applicant: Adobe Inc. ,  Pranav Aggarwal ,  Di Pu ,  Daniel ReMine ,  Ajinkya Kale

Inventor： Pranav Aggarwal ,  Di Pu ,  Daniel ReMine ,  Ajinkya Kale

IPC: G06F40/279

CPC classification number: G06F40/279

Abstract: Disclosed are computer-implemented methods and systems for generating text descriptive of digital images, comprising using a machine learning model to pre-process an image to generate initial text descriptive of the image; adjusting one or more inferences of the machine learning model, the inferences biasing the machine learning model away from associating negative words with the image; using the machine learning model comprising the adjusted inferences to post-process the image to generate updated text descriptive of the image; and processing the generated updated text descriptive of the image outputted by the machine learning model to fine-tune the updated text descriptive of the image.

公开(公告)号：US20220156992A1

公开(公告)日：2022-05-19

申请号：US16952008

申请日：2020-11-18

Applicant: Adobe Inc.

Inventor： Midhun Harikumar ,  Pranav Aggarwal ,  Baldo Faieta ,  Ajinkya Kale ,  Zhe Lin

IPC: G06T11/60 ,  G06T7/11 ,  G06T7/162

Abstract: A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, by a model that includes trainable components, a learned image representation of a target image. The operations further include generating, by a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include generating a class activation map of the target image by, at least, convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image using the class activation map of the target image.

公开(公告)号：US20220138402A1

公开(公告)日：2022-05-05

申请号：US17090055

申请日：2020-11-05

Applicant: ADOBE INC.

Inventor： William Frederick Kraus ,  Nathaniel Joseph Grabaskas ,  Ajinkya Kale

IPC: G06F40/109 ,  G06T11/60 ,  G06T11/20 ,  G06N3/08

Abstract: Embodiments provide systems, methods, and computer storage media for text style suggestions and/or text emphasis suggestions. In an example embodiment, an electronic design application provides a text style suggestion tool that generates text style suggestions to stylize a selected text element based on the context of the design. A text emphasis tool allows a user to select a text element and generate text emphasis suggestions for which words should be emphasized with a different text styling. Various interaction elements allow the user to iterate through the suggestions. For example, a set of style suggestions may be mapped to successive rotational increments around a style wheel, and as the user rotates through the positions on the style wheel, a corresponding text style suggestion is previewed and/or applied.

公开(公告)号：US20210034657A1

公开(公告)日：2021-02-04

申请号：US16525366

申请日：2019-07-29

Applicant: Adobe Inc.

Inventor： Ajinkya Kale ,  Baldo Faieta ,  Benjamin Leviant ,  Fengbin Chen ,  Francois Guerin ,  Kate Sousa ,  Trung Bui ,  Venkat Barakam ,  Zhe Lin

IPC: G06F16/48 ,  G06K9/62 ,  G06F16/43 ,  G06F16/2457

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

公开(公告)号：US12260480B2

公开(公告)日：2025-03-25

申请号：US18178791

申请日：2023-03-06

Applicant: Adobe Inc.

Inventor： Sukriti Verma ,  Venkata naveen kumar Yadav Marri ,  Ritiz Tambi ,  Pranav Vineet Aggarwal ,  Peter O'Donovan ,  Midhun Harikumar ,  Ajinkya Kale

IPC: G06T11/60 ,  G06F3/0482

Abstract: Embodiments are disclosed for machine learning-based generation of recommended layouts. The method includes receiving a set of design elements for performing generative layout recommendation. A number of each type of design element from the set of design elements is determined. A set of recommended layouts are generated using a trained generative layout model and the number and type of design elements. The set of recommended layouts are output.

公开(公告)号：US20230315988A1

公开(公告)日：2023-10-05

申请号：US18315391

申请日：2023-05-10

Applicant: Adobe Inc.

Inventor： Pranav Aggarwal ,  Di Pu ,  Daniel ReMine ,  Ajinkya Kale

IPC: G06F40/279

CPC classification number: G06F40/279

Abstract: Disclosed are computer-implemented methods and systems for generating text descriptive of digital images, comprising using a machine learning model to pre-process an image to generate initial text descriptive of the image; adjusting one or more inferences of the machine learning model, the inferences biasing the machine learning model away from associating negative words with the image; using the machine learning model comprising the adjusted inferences to post-process the image to generate updated text descriptive of the image; and processing the generated updated text descriptive of the image outputted by the machine learning model to fine-tune the updated text descriptive of the image.

公开(公告)号：US11741157B2

公开(公告)日：2023-08-29

申请号：US17544689

申请日：2021-12-07

Applicant: Adobe Inc.

Inventor： Ajinkya Kale ,  Baldo Faieta ,  Benjamin Leviant ,  Fengbin Chen ,  Francois Guerin ,  Kate Sousa ,  Trung Bui ,  Venkat Barakam ,  Zhe Lin

IPC: G06F16/40 ,  G06F16/58 ,  G06F16/48 ,  G06F16/2457 ,  G06F16/43 ,  G06V20/00 ,  G06F18/23213

CPC classification number: G06F16/5866 ,  G06F16/24578 ,  G06F16/43 ,  G06F16/48 ,  G06F18/23213 ,  G06V20/35 ,  G06V2201/10

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for determining multi-term contextual tags for digital content and propagating the multi-term contextual tags to additional digital content. For instance, the disclosed systems can utilize search query supervision to determine and associate multi-term contextual tags (e.g., tags that represent a specific concept based on the order of the terms in the tag) with digital content. Furthermore, the disclosed systems can propagate the multi-term contextual tags determined for the digital content to additional digital content based on similarities between the digital content and additional digital content (e.g., utilizing clustering techniques). Additionally, the disclosed systems can provide digital content as search results based on the associated multi-term contextual tags.

公开(公告)号：US11734339B2

公开(公告)日：2023-08-22

申请号：US17075450

申请日：2020-10-20

Applicant: Adobe Inc.

Inventor： Ajinkya Kale ,  Zhe Lin ,  Pranav Aggarwal

IPC: G06F16/535 ,  G06F16/538 ,  G06F16/242 ,  G06F40/279 ,  G06N3/08 ,  G06N3/04 ,  G06F18/21

CPC classification number: G06F16/535 ,  G06F16/243 ,  G06F16/538 ,  G06F18/21 ,  G06F40/279 ,  G06N3/04 ,  G06N3/08

Abstract: The present disclosure relates to methods, systems, and non-transitory computer-readable media for retrieving digital images in response to queries. For example, in one or more embodiments, the disclosed systems receive a query comprising text and generates a cross-lingual-multimodal embedding for the text within a multimodal embedding space. The disclosed systems further identifies an image embedding for a digital image that corresponds to (e.g., is relevant to) the text from the query based on an embedding distance between the image embedding and the cross-lingual-multimodal embedding for the text within the multimodal embedding space. Accordingly, the disclosed systems retrieve the digital image associated with the image embedding for display on a client device, such as the client device that submitted the query.

公开(公告)号：US20230206525A1

公开(公告)日：2023-06-29

申请号：US18117155

申请日：2023-03-03

Applicant: Adobe Inc.

Inventor： Midhun Harikumar ,  Pranav Aggarwal ,  Baldo Faieta ,  Ajinkya Kale ,  Zhe Lin

IPC: G06T11/60 ,  G06T7/11 ,  G06T7/162

CPC classification number: G06T11/60 ,  G06T7/11 ,  G06T7/162 ,  G06T2207/20084 ,  G06T2207/20081

Abstract: A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, using a model, a learned image representation of a target image. The operations further include generating, using a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image based on the convolving of the learned image representation of the target image with the text embedding.