公开(公告)号：US20240354335A1

公开(公告)日：2024-10-24

申请号：US18760743

申请日：2024-07-01

申请人： Unknot Inc.

发明人： Ross F. Elliot ,  Seth Haberman ,  Michael A. Baumer ,  Nakul Dawra

IPC分类号： G06F16/532 ,  G06F16/535 ,  G06F18/2113 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06T9/00 ,  G06V10/82 ,  G06V30/19 ,  G06V30/194

CPC分类号： G06F16/532 ,  G06F16/535 ,  G06F18/2113 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06T9/002 ,  G06V10/82 ,  G06V30/19173 ,  G06V30/194 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Systems and methods for viewing, storing, transmitting, searching, and editing application-specific audiovisual content (or other unstructured data) are disclosed in which edge devices generate content on the fly from a partial set of instructions rather than merely accessing the content in its final or near-final form. An image processing architecture may include a generative model that may be a deep learning model. The generative model may include a latent space comprising a plurality of latent codes and a trained generator mapping. The trained generator mapping may convert points in the latent space to uncompressed data points, which in the case of audiovisual content may be generated image frames. The generative model may be capable of closely approximating (up to noise or perceptual error) most or all potential data points in the relevant compression application, which in the case of audiovisual content may be source images.

公开(公告)号：US20240354334A1

公开(公告)日：2024-10-24

申请号：US18760734

申请日：2024-07-01

申请人： Unknot Inc.

发明人： Ross F. Elliot ,  Seth Haberman ,  Michael A. Baumer ,  Nakul Dawra

IPC分类号： G06F16/532 ,  G06F16/535 ,  G06F18/2113 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06T9/00 ,  G06V10/82 ,  G06V30/19 ,  G06V30/194

CPC分类号： G06F16/532 ,  G06F16/535 ,  G06F18/2113 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06T9/002 ,  G06V10/82 ,  G06V30/19173 ,  G06V30/194 ,  G06T2207/20081 ,  G06T2207/20084

摘要： Systems and methods for viewing, storing, transmitting, searching, and editing application-specific audiovisual content (or other unstructured data) are disclosed in which edge devices generate content on the fly from a partial set of instructions rather than merely accessing the content in its final or near-final form. An image processing architecture may include a generative model that may be a deep learning model. The generative model may include a latent space comprising a plurality of latent codes and a trained generator mapping. The trained generator mapping may convert points in the latent space to uncompressed data points, which in the case of audiovisual content may be generated image frames. The generative model may be capable of closely approximating (up to noise or perceptual error) most or all potential data points in the relevant compression application, which in the case of audiovisual content may be source images.

公开(公告)号：US20240354333A1

公开(公告)日：2024-10-24

申请号：US18434246

申请日：2024-02-06

申请人： Etsy, Inc.

发明人： Eden Dolev ,  Alaa Awad

IPC分类号： G06F16/532 ,  G06F16/538 ,  G06F16/55

CPC分类号： G06F16/532 ,  G06F16/538 ,  G06F16/55

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for searching with images One of the methods includes receiving a query requesting to search a dataset of images using a first input image; inputting the first image data into a multi-task classification model trained to identify one or more images from the dataset of images; obtaining, as output from a layer of the neural network preceding the plurality of classification heads used for training and in response to the first image data, a first embedding for the first image data; identifying, using the first embedding and from among a plurality of embeddings corresponding to images in the dataset of images, a set of images that are similar to the first input image; and providing, in response to the received query and for display on a client device, the set of images.

公开(公告)号：US12111864B2

公开(公告)日：2024-10-08

申请号：US17414802

申请日：2019-12-24

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Jungho Park ,  Yunsu Lee ,  Jaehun Lee ,  Mirae Jeong ,  Jiyoung Kang ,  Sejin Kwak

IPC分类号： G06F16/00 ,  G06F16/532 ,  G06F16/583 ,  G06F16/9032 ,  G06F16/951 ,  G06F16/9537 ,  G06N3/042 ,  G06N3/045 ,  G06N5/022 ,  G06N20/00 ,  G06V20/20 ,  H04L67/50 ,  G06Q30/0601

CPC分类号： G06F16/532 ,  G06F16/5846 ,  G06F16/5854 ,  G06F16/90332 ,  G06F16/951 ,  G06F16/9537 ,  G06N3/042 ,  G06N3/045 ,  G06N5/022 ,  G06V20/20 ,  H04L67/535 ,  G06Q30/0625

摘要： An electronic device is disclosed. The electronic device comprises: a memory including at least one command; and a processor connected to the memory to control the electronic device, wherein by executing the at least one command, the processor obtains an image according to a user's interaction with the electronic device, obtains information about the user's intention according to information about an object obtained from the image and context information obtained during the interaction, and obtains information concerning the obtained object from a knowledge base stored in the memory, according to the information about the user's intention, wherein the knowledge base includes device information about a plurality of electronic devices used during the user's activity, object information about a plurality of objects obtained according to the activity, and intention information corresponding to correlative information, and the processor obtains, from the knowledge base, information concerning the obtained object according to the intention information corresponding to the obtained object.

公开(公告)号：US12080042B2

公开(公告)日：2024-09-03

申请号：US17377609

申请日：2021-07-16

申请人： Taiwan Semiconductor Manufacturing Company, Ltd.

发明人： Katherine Chiang

IPC分类号： G06F16/50 ,  G06F16/532 ,  G06F17/16 ,  G06V10/44

CPC分类号： G06V10/44 ,  G06F16/532 ,  G06F17/16

摘要： Methods for retrieving images from a database are provided. A query image is obtained. A plurality of patches are extracted from the query image. A set of weightings is obtained according to a plurality of bases of a sparsity-based dictionary. The set of weightings includes a plurality of non-zero weightings. The patches are encoded with the set of weightings to obtain an encoding matrix. The database is searched based on the encoding matrix to retrieve the images corresponding to the query image. The database and the dictionary are dynamically updated to adapt to the query image encountered.

公开(公告)号：US12026192B2

公开(公告)日：2024-07-02

申请号：US17781093

申请日：2021-04-30

申请人： BOE TECHNOLOGY GROUP CO., LTD.

发明人： Jingtao Xu ,  Shaonan Zhang

IPC分类号： G06F7/00 ,  G06F16/532 ,  G06F16/538 ,  G06F16/583 ,  G06V10/40 ,  G06V10/774

CPC分类号： G06F16/532 ,  G06F16/538 ,  G06F16/583 ,  G06V10/40 ,  G06V10/774

摘要： An image retrieval method, an image retrieval device, and an image retrieval system, which are used for image retrieval, are provided. The image retrieval method comprises: receiving a first original image (S100); extracting an image feature of the first original image to obtain a first feature code (S200); obtaining first target information according to the first feature code (S300); according to the first target information, searching for a first target painting set corresponding to the first target information in at least one of a painting library and a knowledge graph library, so as to obtain the first target painting set (S400); and outputting the first target painting set (S500).

公开(公告)号：US12020477B2

公开(公告)日：2024-06-25

申请号：US18110415

申请日：2023-02-16

申请人： HURON TECHNOLOGIES INTERNATIONAL INC.

发明人： Hamid Reza Tizhoosh ,  Savvas Damaskinos ,  Arthur Edward Dixon

IPC分类号： G06K9/00 ,  G06F16/532 ,  G06F16/55 ,  G06F16/56 ,  G06T7/10 ,  G06T9/00 ,  G06V10/44 ,  G06V10/762 ,  G06V10/764 ,  G06V10/77 ,  G06V10/82

CPC分类号： G06V10/82 ,  G06F16/532 ,  G06F16/55 ,  G06F16/56 ,  G06T7/10 ,  G06T9/002 ,  G06V10/44 ,  G06V10/762 ,  G06V10/764 ,  G06V10/77 ,  G06T2207/20021

摘要： Computer-implemented methods and systems are provided for generating encoded representations for multiple magnifications of one or more query images. An example method for involves operating a processor to obtain a query image and identify a set of anchor points within the query image. The processor is operable to generate a plurality of sub-images for a plurality of magnification levels for each anchor point. Each sub-image includes the anchor point and corresponds to a magnification level of the plurality of magnification levels. The processor is operable to, for each magnification level, apply an artificial neural network model to a group of sub-images having that magnification level to extract a feature vector representative of image characteristics of the query image at that magnification level; and to generate an encoded representation for multiple magnifications of the query image based on the feature vectors extracted for the plurality of magnification levels.

公开(公告)号：US20240202780A1

公开(公告)日：2024-06-20

申请号：US18589855

申请日：2024-02-28

申请人： MediaLab.AI

发明人： Michael Heyward ,  Maarten Bosma ,  Samuel Brotherton ,  Charles DePue, III ,  Manuel Ernesto Gomez Contreras ,  Chase Evans

IPC分类号： G06Q30/0251 ,  G06F16/532 ,  G06F16/58 ,  G06F16/583 ,  G06F16/9535 ,  G06F16/9536 ,  G06F16/9538 ,  G06Q50/00

CPC分类号： G06Q30/0269 ,  G06F16/532 ,  G06F16/58 ,  G06F16/5838 ,  G06F16/5846 ,  G06F16/9535 ,  G06F16/9536 ,  G06F16/9538 ,  G06Q50/01

摘要： A system for selecting an image to accompany text from a user in connection with a social media post. The system includes receiving text from the user; identifying one or more search terms based on the text; identifying candidate images from images in one or more image databases using the search terms, where the candidate images comprise a sponsored image; presenting one or more candidate images to the user, where the sponsored image is presented preferentially compared to other candidate images; receiving from the user a selected image from the one or more candidate images; generating the social media post comprising the selected image and the user-submitted text; and transmitting the social media post for display.

公开(公告)号：US20240185551A1

公开(公告)日：2024-06-06

申请号：US18074991

申请日：2022-12-05

申请人： Microsoft Technology Licensing, LLC

发明人： Rishu AGGARWAL

IPC分类号： G06V10/22 ,  G06F16/532 ,  G06T3/20 ,  G06T11/00 ,  G06V10/44 ,  G06V10/74 ,  G06V10/774

CPC分类号： G06V10/235 ,  G06F16/532 ,  G06T3/20 ,  G06T11/00 ,  G06V10/44 ,  G06V10/761 ,  G06V10/774 ,  G06F3/0488 ,  G06T2200/24

摘要： This document relates to searching for images using a query image. For example, an input image can be received and analyzed to identify objects, and then identification of two or more selected objects can be received. A query image can be derived from the input image, where the query image includes the selected objects. The query image can be used to perform a search to identify related images, which can be output in response to the query image.

公开(公告)号：US20240184821A1

公开(公告)日：2024-06-06

申请号：US18163114

申请日：2023-02-01

申请人： Unknot Inc.

发明人： Ross F. Elliot ,  Seth Haberman ,  Michael A. Baumer ,  Nakul Dawra

IPC分类号： G06F16/532 ,  G06F16/535 ,  G06F18/2113 ,  G06N3/08 ,  G06T9/00 ,  G06V10/82 ,  G06V30/19 ,  G06V30/194

CPC分类号： G06F16/532 ,  G06F16/535 ,  G06F18/2113 ,  G06N3/08 ,  G06T9/002 ,  G06V10/82 ,  G06V30/19173 ,  G06V30/194

摘要： Systems and methods for viewing, storing, transmitting, searching, and editing application-specific audiovisual content (or other unstructured data) are disclosed in which edge devices generate content on the fly from a partial set of instructions rather than merely accessing the content in its final or near-final form. An image processing architecture may include a generative model that may be a deep learning model. The generative model may include a latent space comprising a plurality of latent codes and a trained generator mapping. The trained generator mapping may convert points in the latent space to uncompressed data points, which in the case of audiovisual content may be generated image frames. The generative model may be capable of closely approximating (up to noise or perceptual error) most or all potential data points in the relevant compression application, which in the case of audiovisual content may be source images.