中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5372 records (took 0.037 seconds)

    Context-based organization of digital media
    51.
    发明授权
    Context-based organization of digital media 有权

    公开(公告)号：US12216704B2

    公开(公告)日：2025-02-04

    申请号：US16591913

    申请日：2019-10-03

    Applicant: ADOBE INC.

    Inventor： Rotish Kumar ,  Arshla Jindal ,  Abhishek Shah

    IPC: G06F16/583 ,  G06F16/538 ,  G06F16/54 ,  G06F16/58 ,  G06F16/587

    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for organization of digital media in which a digital media gallery is organized based on underlying events or occasions by leveraging content tags associated with media. Content tags and their corresponding confidence scores for a set of media are compared with correlation scores of content tags with certain event types. Upon receipt of a set of media, candidate event types may be determined based on content tags associated with the set of media and relevant tags for different event types. The candidate event types are scored based on the confidence scores and the correlations scores for each candidate event type. The highest scoring candidate event type may be presented to the user as the event type for the set of media.

    GAN IMAGE GENERATION FROM FEATURE REGULARIZATION
    52.
    发明申请
    GAN IMAGE GENERATION FROM FEATURE REGULARIZATION 有权

    公开(公告)号：US20250037431A1

    公开(公告)日：2025-01-30

    申请号：US18357621

    申请日：2023-07-24

    Applicant: ADOBE INC.

    Inventor： Min Jin Chong ,  Krishna Kumar Singh ,  Yijun Li ,  Jingwan Lu

    IPC: G06V10/774 ,  G06N3/045 ,  G06N3/0475

    Abstract: Systems and methods for training a Generative Adversarial Network (GAN) using feature regularization are described herein. Embodiments are configured to generate a candidate image using a generator network of a GAN, classify the candidate image as real or generated using a discriminator network of the GAN, and train the GAN to generate realistic images based on the classifying of the candidate image. The training process includes regularizing a gradient with respect to features extracted using a discriminator network of the GAN.

    Connecting paths based on primitives
    55.
    发明授权
    Connecting paths based on primitives 有权

    公开(公告)号：US12205200B2

    公开(公告)日：2025-01-21

    申请号：US18114755

    申请日：2023-02-27

    Applicant: Adobe Inc.

    Inventor： Tarun Gehlaut ,  Sasha Makkar ,  Arshdeep Singh Chugh

    IPC: G06T11/20

    Abstract: In implementation of techniques for connecting paths based on primitives, a computing device implements a path connection system to receive a first path and a second path displayed in a user interface. The path connection system determines an end section of the first path and a corresponding end section of the second path. Based on the on the end section of the first path, the path connection system identifies a first primitive. Based on the corresponding end section of the second path, the path connection system identifies a second primitive. The path connection system then generates a connection path for display relative to the first path and the second path in the user interface by generating a Bezier curve based on the first primitive and the second primitive.

    TEXT-CONDITIONED VISUAL ATTENTION FOR MULTIMODAL MACHINE LEARNING MODELS
    56.
    发明申请
    TEXT-CONDITIONED VISUAL ATTENTION FOR MULTIMODAL MACHINE LEARNING MODELS 有权

    公开(公告)号：US20250022263A1

    公开(公告)日：2025-01-16

    申请号：US18351211

    申请日：2023-07-12

    Applicant: Adobe Inc.

    Inventor： Prateksha Udhayanan ,  Srikrishna Karanam ,  Balaji Vasan Srinivasan

    IPC: G06V10/80 ,  G06T11/60 ,  G06V10/82

    Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for conditioning images on modification texts to generate multi-modal gradient attention maps. In particular, in some embodiments, the disclosed systems generate, utilizing a vision-language neural network of an image-text comparison machine learning model, a reference text-image feature vector based on a reference image and a modification text. Additionally, in some embodiments, the disclosed systems generate, utilizing the vision-language neural network of the image-text comparison machine learning model, a target text-image feature vector based on a target image and the modification text. Moreover, in some implementations, the disclosed systems generate, from the reference text-image feature vector and the target text-image feature vector, a multi-modal gradient attention map reflecting a visual grounding of the image-text comparison machine learning model relative to the modification text.

    Systems for generating indications of relationships between electronic documents
    57.
    发明授权
    Systems for generating indications of relationships between electronic documents 有权

    公开(公告)号：US12198459B2

    公开(公告)日：2025-01-14

    申请号：US17534744

    申请日：2021-11-24

    Applicant: Adobe Inc.

    Inventor： Natwar Modani ,  Vaidehi Ramesh Patil ,  Inderjeet Jayakumar Nair ,  Gaurav Verma ,  Anurag Maurya ,  Anirudh Kanfade

    IPC: G06K9/34 ,  G06V30/19 ,  G06V30/262 ,  G06V30/413 ,  G06V30/414 ,  G06V30/418

    Abstract: In implementations of systems for generating indications of relationships between electronic documents, a processing device implements a relationship system to segment text of electronic documents included in a document corpus into segments. The relationship system determines a subset of the electronic documents that includes electronic document pairs having a number of similar segments that is greater than a threshold number. The similar segments are identified using locality sensitive hashing. The electronic document pairs are classified as related documents or unrelated documents using a machine learning model that receives a pair of electronic documents as an input and generates an indication of a classification for the pair of electronic documents as an output. Indications of relationships between particular electronic documents included in the subset are generated based at least partially on the electronic document pairs that are classified as related documents.

    Applying vector-based decals on three-dimensional objects
    58.
    发明授权
    Applying vector-based decals on three-dimensional objects 有权

    公开(公告)号：US12198284B2

    公开(公告)日：2025-01-14

    申请号：US18054248

    申请日：2022-11-10

    Applicant: Adobe Inc.

    Inventor： Sumit Dhingra ,  Siddhartha Chaudhuri ,  Vineet Batra

    IPC: G06T19/20 ,  G06T7/13

    Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that apply a resolution independent, vector-based decal on a 3D object. In one or more implementations, the disclosed systems apply piecewise non-linear transformation on an input decal vector geometry to align the decal with a surface of an underlying 3D object. To apply a vector-based decal on a 3D object, in certain embodiments, the disclosed systems parameterize a 3D mesh of the 3D object to create a mesh map. Moreover, in some instances, the disclosed systems determine intersections between edges of a decal geometry and edges of the mesh map to add vertices to the decal geometry at the intersections. Additionally, in some implementations, the disclosed systems lift and project vertices of the decal geometry into three dimensions to align the vertices with faces of the 3D mesh of the 3D object.

Patent Agency Ranking