公开(公告)号：US20220391611A1

公开(公告)日：2022-12-08

申请号：US17341778

申请日：2021-06-08

Applicant: ADOBE INC.

Inventor： RATHEESH KALAROT ,  Siavash Khodadadeh ,  Baldo Faieta ,  Shabnam Ghadar ,  Saeid Motiian ,  Wei-An Lin ,  Zhe Lin

IPC: G06K9/00 ,  G06N3/08 ,  G06N3/04 ,  G06T11/60

Abstract: Systems and methods for image processing are described. One or more embodiments of the present disclosure identify a latent vector representing an image of a face, identify a target attribute vector representing a target attribute for the image, generate a modified latent vector using a mapping network that converts the latent vector and the target attribute vector into a hidden representation having fewer dimensions than the latent vector, wherein the modified latent vector is generated based on the hidden representation, and generate a modified image based on the modified latent vector, wherein the modified image represents the face with the target attribute.

公开(公告)号：US20220284321A1

公开(公告)日：2022-09-08

申请号：US17190668

申请日：2021-03-03

Applicant: ADOBE INC.

Inventor： Xin Yuan ,  Zhe Lin ,  Jason Wen Yong Kuen ,  Jianming Zhang ,  Yilin Wang ,  Ajinkya Kale ,  Baldo Faieta

IPC: G06N5/04 ,  G06N20/00

Abstract: Systems and methods for multi-modal representation learning are described. One or more embodiments provide a visual representation learning system trained using machine learning techniques. For example, some embodiments of the visual representation learning system are trained using cross-modal training tasks including a combination of intra-modal and inter-modal similarity preservation objectives. In some examples, the training tasks are based on contrastive learning techniques.

公开(公告)号：US20220277039A1

公开(公告)日：2022-09-01

申请号：US17186625

申请日：2021-02-26

Applicant: ADOBE INC.

Inventor： PRANAV AGGARWAL ,  Ajinkya Kale ,  Baldo Faieta ,  Saeid Motiian ,  Venkata naveen kumar yadav Marri

IPC: G06F16/583 ,  G06F40/279 ,  G06K9/46 ,  G06F16/532 ,  G06F16/51 ,  G06F16/538 ,  G06N3/08

Abstract: The present disclosure describes systems and methods for information retrieval. Embodiments of the disclosure provide a color embedding network trained using machine learning techniques to generate embedded color representations for color terms included in a text search query. For example, techniques described herein are used to represent color text in a same space as color embeddings (e.g., an embedding space created by determining a histogram of LAB based colors in a three-dimensional (3D) space). Further, techniques are described for indexing color palettes for all the searchable images in the search space. Accordingly, color terms in a text query are directly converted into a color palette and an image search system can return one or more search images with corresponding color palettes that are relevant to (e.g., within a threshold distance from) the color palette of the text query.

公开(公告)号：US20220092108A1

公开(公告)日：2022-03-24

申请号：US17025041

申请日：2020-09-18

Applicant: Adobe Inc.

Inventor： John Collomosse ,  Zhe Lin ,  Saeid Motiian ,  Hailin Jin ,  Baldo Faieta ,  Alex Filipkowski

IPC: G06F16/583 ,  G06F16/535 ,  G06F16/532 ,  G06N3/08

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly identifying digital images with similar style to a query digital image using fine-grain style determination via weakly supervised style extraction neural networks. For example, the disclosed systems can extract a style embedding from a query digital image using a style extraction neural network such as a novel two-branch autoencoder architecture or a weakly supervised discriminative neural network. The disclosed systems can generate a combined style embedding by combining complementary style embeddings from different style extraction neural networks. Moreover, the disclosed systems can search a repository of digital images to identify digital images with similar style to the query digital image. The disclosed systems can also learn parameters for one or more style extraction neural network through weakly supervised training without a specifically labeled style ontology for sample digital images.

公开(公告)号：US11232147B2

公开(公告)日：2022-01-25

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: G06F16/20 ,  G06F16/48 ,  G06K9/62 ,  G06F16/2457 ,  G06F16/43

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：US10789525B2

公开(公告)日：2020-09-29

申请号：US15002172

申请日：2016-01-20

Applicant: ADOBE INC.

Inventor： Bernard James Kerr ,  Zhe Lin ,  Patrick Reynolds ,  Baldo Faieta

IPC: G06F17/00 ,  G06F7/00 ,  G06N3/02 ,  G06F16/583 ,  G06F3/0484

Abstract: In various implementations, one or more specific attributes found in an image can be modified utilizing one or more specific attributes found in another image. Machine learning, deep neural networks, and other computer vision techniques can be utilized to extract attributes of images, such as color, composition, font, style, and texture from one or more images. A user may modify at least one of these attributes in a first image based on the attribute(s) of another image and initiate a visual-based search using the modified image.

公开(公告)号：US10592548B2

公开(公告)日：2020-03-17

申请号：US14828085

申请日：2015-08-17

Applicant: Adobe Inc.

Inventor： Zeke Koch ,  Baldo Faieta ,  Jen-Chan Chien ,  Mark M. Randall ,  Olivier Sirven ,  Philipp Koch ,  Dennis G. Nicholson

IPC: G06F16/58 ,  G06F21/10

Abstract: Image search persona techniques and systems are described. In one or more implementations, a digital medium environment is described for controlling image searches by one or more computing devices. An image search request and an indication of one or more personas of one or more respective users associated with the image search request is received by the one or more computing devices. The one or more personas specify characteristics of the one or more respective users themselves. A plurality of images are obtained by the one or more computing devices based on the image search request. The plurality of images are filtered by the one or more computing devices based on the one or more personas and a search result is generated by the one or more computing devices from the filtered plurality of images.

公开(公告)号：US12093308B2

公开(公告)日：2024-09-17

申请号：US17453595

申请日：2021-11-04

Applicant: ADOBE INC.

Inventor： Baldo Faieta ,  Ajinkya Gorakhnath Kale ,  Pranav Vineet Aggarwal ,  Naveen Marri ,  Saeid Motiian ,  Tracy Holloway King ,  Alex Filipkowski ,  Shabnam Ghadar

IPC: G06F16/583 ,  G06F16/535 ,  G06F16/538 ,  G06F16/58 ,  G06F40/295 ,  G06N3/08

CPC classification number: G06F16/5838 ,  G06F16/535 ,  G06F16/538 ,  G06F16/5866 ,  G06F40/295 ,  G06N3/08

Abstract: Systems and methods for image retrieval are described. Embodiments of the present disclosure receive a search query from a user; extract an entity and a color phrase describing the entity from the search query; generate an entity color embedding in a color embedding space from the color phrase using a multi-modal color encoder; identify an image in a database based on metadata for the image including an object label corresponding to the extracted entity and an object color embedding in the color embedding space corresponding to the object label; and provide image information for the image to the user based on the metadata.

公开(公告)号：US12014452B2

公开(公告)日：2024-06-18

申请号：US18449604

申请日：2023-08-14

Applicant: Adobe Inc.

Inventor： Akhilesh Kumar ,  Baldo Faieta ,  Piotr Walczyszyn ,  Ratheesh Kalarot ,  Archie Bagnall ,  Shabnam Ghadar ,  Wei-An Lin ,  Cameron Smith ,  Christian Cantrell ,  Patrick Hebron ,  Wilson Chan ,  Jingwan Lu ,  Holger Winnemoeller ,  Sven Olsen

IPC: G06T11/60 ,  G06N3/04 ,  G06T11/20

CPC classification number: G06T11/60 ,  G06N3/04 ,  G06T11/203

Abstract: The present disclosure describes systems, methods, and non-transitory computer readable media for detecting user interactions to edit a digital image from a client device and modify the digital image for the client device by using a web-based intermediary that modifies a latent vector of the digital image and an image modification neural network to generate a modified digital image from the modified latent vector. In response to user interaction to modify a digital image, for instance, the disclosed systems modify a latent vector extracted from the digital image to reflect the requested modification. The disclosed systems further use a latent vector stream renderer (as an intermediary device) to generate an image delta that indicates a difference between the digital image and the modified digital image. The disclosed systems then provide the image delta as part of a digital stream to a client device to quickly render the modified digital image.

公开(公告)号：US11887216B2

公开(公告)日：2024-01-30

申请号：US17455796

申请日：2021-11-19

Applicant: ADOBE INC.

Inventor： Ratheesh Kalarot ,  Timothy M. Converse ,  Shabnam Ghadar ,  John Thomas Nack ,  Jingwan Lu ,  Elya Shechtman ,  Baldo Faieta ,  Akhilesh Kumar

IPC: G06T5/00 ,  G06T11/00 ,  G06N3/08 ,  G06V40/16

CPC classification number: G06T11/00 ,  G06N3/08 ,  G06V40/168 ,  G06V40/172

Abstract: The present disclosure describes systems and methods for image processing. Embodiments of the present disclosure include an image processing apparatus configured to generate modified images (e.g., synthetic faces) by conditionally changing attributes or landmarks of an input image. A machine learning model of the image processing apparatus encodes the input image to obtain a joint conditional vector that represents attributes and landmarks of the input image in a vector space. The joint conditional vector is then modified, according to the techniques described herein, to form a latent vector used to generate a modified image. In some cases, the machine learning model is trained using a generative adversarial network (GAN) with a normalization technique, followed by joint training of a landmark embedding and attribute embedding (e.g., to reduce inference time).