中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

34 records (took 0.033 seconds)

    GENERATING SCENE GRAPHS FROM DIGITAL IMAGES USING EXTERNAL KNOWLEDGE AND IMAGE RECONSTRUCTION
    24.
    发明申请
    GENERATING SCENE GRAPHS FROM DIGITAL IMAGES USING EXTERNAL KNOWLEDGE AND IMAGE RECONSTRUCTION 有权

    公开(公告)号：US20220309762A1

    公开(公告)日：2022-09-29

    申请号：US17805289

    申请日：2022-06-03

    Applicant: Adobe Inc.

    Inventor： Handong Zhao ,  Zhe Lin ,  Sheng Li ,  Mingyang Ling ,  Jiuxiang Gu

    IPC: G06V10/26 ,  G06N3/08 ,  G06K9/62 ,  G06N3/04 ,  G06V10/426

    Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating semantic scene graphs for digital images using an external knowledgebase for feature refinement. For example, the disclosed system can determine object proposals and subgraph proposals for a digital image to indicate candidate relationships between objects in the digital image. The disclosed system can then extract relationships from an external knowledgebase for refining features of the object proposals and the subgraph proposals. Additionally, the disclosed system can generate a semantic scene graph for the digital image based on the refined features of the object/subgraph proposals. Furthermore, the disclosed system can update/train a semantic scene graph generation network based on the generated semantic scene graph. The disclosed system can also reconstruct the image using object labels based on the refined features to further update/train the semantic scene graph generation network.

    KNOWLEDGE DISTILLATION FOR NEURAL NETWORKS USING MULTIPLE AUGMENTATION STRATEGIES
    25.
    发明申请
    KNOWLEDGE DISTILLATION FOR NEURAL NETWORKS USING MULTIPLE AUGMENTATION STRATEGIES 有权

    公开(公告)号：US20220108131A1

    公开(公告)日：2022-04-07

    申请号：US17062157

    申请日：2020-10-02

    Applicant: Adobe Inc.

    Inventor： Jason Wen Yong Kuen ,  Zhe Lin ,  Jiuxiang Gu

    IPC: G06K9/62 ,  G06N3/04 ,  G06T3/40 ,  G06T3/60

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and efficiently learning parameters of a distilled neural network from parameters of a source neural network utilizing multiple augmentation strategies. For example, the disclosed systems can generate lightly augmented digital images and heavily augmented digital images. The disclosed systems can further learn parameters for a source neural network from the lightly augmented digital images. Moreover, the disclosed systems can learn parameters for a distilled neural network from the parameters learned for the source neural network. For example, the disclosed systems can compare classifications of heavily augmented digital images generated by the source neural network and the distilled neural network to transfer learned parameters from the source neural network to the distilled neural network via a knowledge distillation loss function.

    GENERATING TEMPORAL DEPENDENCY GRAPHS
    26.
    发明申请
    GENERATING TEMPORAL DEPENDENCY GRAPHS 有权

    公开(公告)号：US20250013831A1

    公开(公告)日：2025-01-09

    申请号：US18493465

    申请日：2023-10-24

    Applicant: Adobe Inc. ,  University of Maryland

    Inventor： Puneet Mathur ,  Vlad Morariu ,  Verena Kaynig-Fittkau ,  Jiuxiang Gu ,  Franck Dernoncourt ,  Quan Tran ,  Ani Nenkova ,  Dinesh Manocha ,  Rajiv Jain

    IPC: G06F40/30

    Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a temporal dependency graph. For example, the disclosed systems generate from a text document, a structural vector, a syntactic vector, and a semantic vector. In some embodiments, the disclosed systems generate a multi-dimensional vector by combining the various vectors. In these or other embodiments, the disclosed systems generate an initial dependency graph structure and an adjacency matrix utilizing an iterative deep graph learning model. Further, in some embodiments, the disclosed systems generate an entity-level relation matrix utilizing a convolutional graph neural network. Moreover, in some embodiments, the disclosed systems generate a temporal dependency graph from the entity-level relation matrix and the adjacency matrix.

    Multi-scale distillation for low-resolution detection
    27.
    发明授权
    Multi-scale distillation for low-resolution detection 有权

    公开(公告)号：US12136185B2

    公开(公告)日：2024-11-05

    申请号：US17455134

    申请日：2021-11-16

    Applicant: ADOBE INC.

    Inventor： Jason Kuen ,  Jiuxiang Gu ,  Zhe Lin

    IPC: G06T3/4046 ,  G06N3/045 ,  G06N3/08 ,  G06V10/75

    Abstract: Systems and methods for image processing are described. The systems and methods include receiving a low-resolution image; generating a feature map based on the low-resolution image using an encoder of a student network, wherein the encoder of the student network is trained based on comparing a predicted feature map from the encoder of the student network and a fused feature map from a teacher network, and wherein the fused feature map represents a combination of first feature map from a high-resolution encoder of the teacher network and a second feature map from a low-resolution encoder of the teacher network; and decoding the feature map to obtain prediction information for the low-resolution image.

    TRAINING LANGUAGE MODELS AND PRESERVING PRIVACY
    29.
    发明公开
    TRAINING LANGUAGE MODELS AND PRESERVING PRIVACY 审中-公开

    公开(公告)号：US20240135103A1

    公开(公告)日：2024-04-25

    申请号：US18173199

    申请日：2023-02-23

    Applicant: Adobe Inc.

    Inventor： Franck Dernoncourt ,  Tong Sun ,  Thi kim phung Lai ,  Rajiv Bhawanji Jain ,  Nikolaos Barmpalios ,  Jiuxiang Gu

    IPC: G06F40/295 ,  G06F40/274

    CPC classification number: G06F40/295 ,  G06F40/274

    Abstract: In implementations of systems for training language models and preserving privacy, a computing device implements a privacy system to predict a next word after a last word in a sequence of words by processing input data using a machine learning model trained on training data to predict next words after last words in sequences of words. The training data describes a corpus of text associated with clients and including sensitive samples and non-sensitive samples. The machine learning model is trained by sampling a client of the clients and using a subset of the sensitive samples associated with the client and a subset of the non-sensitive samples associated with the client to update parameters of the machine learning model. The privacy system generates an indication of the next word after the last word in the sequence of words for display in a user interface.

    Self-supervised document representation learning
    30.
    发明授权
    Self-supervised document representation learning 有权

    公开(公告)号：US11886815B2

    公开(公告)日：2024-01-30

    申请号：US17333892

    申请日：2021-05-28

    Applicant: Adobe Inc.

    Inventor： Jiuxiang Gu ,  Vlad Morariu ,  Varun Manjunatha ,  Tong Sun ,  Rajiv Jain ,  Peizhao Li ,  Jason Kuen ,  Handong Zhao

    IPC: G06F40/279 ,  G06F40/205 ,  G06F16/93 ,  G06F40/30 ,  G06N3/088 ,  G06N3/045

    CPC classification number: G06F40/279 ,  G06F16/93 ,  G06F40/205 ,  G06F40/30 ,  G06N3/045 ,  G06N3/088

    Abstract: One example method involves operations for a processing device that include receiving, by a machine learning model trained to generate a search result, a search query for a text input. The machine learning model is trained by receiving pre-training data that includes multiple documents. Pre-training the machine learning model by generating, using an encoder, feature embeddings for each of the documents included in the pre-training data. The feature embeddings are generated by applying a masking function to visual and textual features in the documents. Training the machine learning model also includes generating, using the feature embeddings, output features for the documents by concatenating the feature embeddings and applying a non-linear mapping to the feature embeddings. Training the machine learning model further includes applying a linear classifier to the output features. Additionally, operations include generating, for display, a search result using the machine learning model based on the input.

Patent Agency Ranking