知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

88 records (took 0.019 seconds)

    REFINED ENTROPY CODING FOR LEVEL MAPS
    11.
    发明申请
    REFINED ENTROPY CODING FOR LEVEL MAPS 审中-公开

    公开(公告)号：US20200053367A1

    公开(公告)日：2020-02-13

    申请号：US16659666

    申请日：2019-10-22

    Applicant: GOOGLE LLC

    Inventor： Joseph Young ,  Dake He

    IPC: H04N19/18 ,  H04N19/44 ,  H04N19/159 ,  H04N19/124 ,  H04N19/129 ,  H04N19/13 ,  H04N19/176 ,  H04N19/184 ,  H04N19/147 ,  H04N19/93 ,  H04N19/91

    Abstract: An apparatus includes a memory and a processor. The processor is configured to execute instructions stored in the memory to obtain a transform type for decoding a transform block for the current block; select, based on the transform type, a template for coding a value of a non-zero map; select, based on the template, a context for entropy decoding the value of the non-zero map; and decode the value of the non-zero map based on the context. The non-zero map indicates which coefficients of the transform block have non-zero values. A method includes obtaining a transform class for coding a transform block for the current block, wherein the transform class corresponding to a transform type and a direction; selecting, based on the transform class, a coding context for coding a value of a non-zero map; and coding the value of the non-zero map based on the coding context.

    CONTEXT MODELING FOR INTRA-PREDICTION MODES
    12.
    发明申请
    CONTEXT MODELING FOR INTRA-PREDICTION MODES 审中-公开

    公开(公告)号：US20200021820A1

    公开(公告)日：2020-01-16

    申请号：US16580226

    申请日：2019-09-24

    Applicant: GOOGLE LLC

    Inventor： Joseph Young ,  Dake He

    IPC: H04N19/18 ,  H04N19/44 ,  H04N19/159 ,  H04N19/124 ,  H04N19/129 ,  H04N19/13 ,  H04N19/176 ,  H04N19/91

    Abstract: A method for coding a current block using an intra-prediction mode includes defining a mapping from available intra-prediction modes to intra-prediction classes; determining, using the mapping, a first intra-prediction class of a first intra-prediction mode used for decoding a first neighboring block of the current block; determining, using the mapping, a second intra-prediction class of a second intra-prediction mode used for decoding a second neighboring block of the current block; using the first intra-prediction class and the second intra-prediction class as indices into a list of available context models to select a context model for coding the intra-prediction mode; and coding the intra-prediction mode using the context model. A first number of the intra-prediction classes is smaller than a second number of the available intra-prediction modes. each class is an ordinal value, and each available intra-prediction mode uniquely maps to one class of the intra-prediction classes.

    USING MULTIPLE PROBABILITY MODELS FOR ENTROPY CODING IN VIDEO COMPRESSION
    13.
    发明申请
    USING MULTIPLE PROBABILITY MODELS FOR ENTROPY CODING IN VIDEO COMPRESSION 审中-公开

    公开(公告)号：US20190394467A1

    公开(公告)日：2019-12-26

    申请号：US16562659

    申请日：2019-09-06

    Applicant: GOOGLE LLC

    Inventor： Dake He

    IPC: H04N19/13 ,  H04N19/18 ,  H04N19/159 ,  H04N19/196 ,  H04N19/124 ,  H04N19/176 ,  H04N19/91 ,  H04N19/96

    Abstract: Entropy encoding and decoding a sequence of symbols using probability mixing is disclosed. A method includes selecting models including a first model and a second model; for at least a symbol, at a position of the symbols, determining a mixed probability using the first model and the second model, by: determining, using the first model, a first conditional probability for coding the symbol, the first conditional probability being a conditional probability of the symbol given a sub-sequence of the sequence having a first value; determining, using the second model, a second conditional probability for coding the symbol, the second conditional probability being a conditional probability of the symbol given the sub-sequence having a second value; and determining, using the first conditional probability and the second conditional probability, the mixed probability for coding the symbol; and coding the symbol using the mixed probability.

    CODING OF MOTION VECTORS
    14.
    发明申请
    CODING OF MOTION VECTORS 审中-公开

    公开(公告)号：US20190191177A1

    公开(公告)日：2019-06-20

    申请号：US15845307

    申请日：2017-12-18

    Applicant: Google LLC

    Inventor： Dake He

    IPC: H04N19/517 ,  H04N19/91 ,  H04N19/61

    Abstract: A method for inter-predicting a current block includes determining a motion vector and a reference frame for the current block, determining a transform block of transform coefficients for the current block, determining a category of the transform block, determining, using the category, a context for coding the motion vector, and encoding the motion vector using the context. The category is based on positions of non-zero coefficients of the transform coefficients. An apparatus for decoding a current block using inter prediction includes a memory and a processor. The memory includes instructions executable by the processor to decode a transform block for the current block, determine a category of the transform block, determine, using the category, a context for decoding a motion vector, decode the motion vector using the context, and inter-predict the current block using the motion vector. The category is based on positions of non-zero coefficients in the transform block.

    CLASSIFYING DATA OBJECTS USING NEIGHBORHOOD REPRESENTATIONS
    15.
    发明申请
    CLASSIFYING DATA OBJECTS USING NEIGHBORHOOD REPRESENTATIONS 有权

    公开(公告)号：US20250086502A1

    公开(公告)日：2025-03-13

    申请号：US18560756

    申请日：2022-12-30

    Applicant: Google LLC

    Inventor： Oleg Golubitsky ,  Dake He

    IPC: G06N20/00

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data objects. One of the methods includes maintaining a dataset including reference data objects that each have one or more labels, one or more features, or both; receiving a request to add, to the dataset, a new data object that has one or more features but is missing one or more labels; selecting N neighbor data objects based on similarity scores of the neighbor data objects with respect to the new data object; generating a neighborhood feature vector for the new data object; processing the neighborhood feature vector using a machine learning model to predict the one or more labels for the new data object; and updating the dataset to include the new data object and to associate the one or more predicted labels with the new data object.

    Local Node Embeddings for Heterogeneous Graphs
    16.
    发明公开
    Local Node Embeddings for Heterogeneous Graphs 审中-公开

    公开(公告)号：US20240289384A1

    公开(公告)日：2024-08-29

    申请号：US18323877

    申请日：2023-05-25

    Applicant: Google LLC

    Inventor： Kimon Fountoulakis ,  Dake He

    IPC: G06F16/901

    CPC classification number: G06F16/9024 ,  G06F16/313

    Abstract: Provided are computing systems, methods, and platforms that obtain local node embeddings for heterogeneous graphs. A heterogeneous graph comprising a plurality of nodes can be obtained. Weight values respectively associated with subgraphs of the heterogeneous graph can be determined. At least one node from among the plurality of nodes can be selected. An embedding for the at least one selected node can be learned using an embedding objective computed based on the weight values. The heterogeneous graph can be processed based on the embedding. Submodular hypergraphs can be used to represent heterogeneous graphs and their cuts. The 1-regularized personalized PageRank can be applied to hypergraphs, where the optimal solution gives the node embedding for the given seed nodes. The resulting 1-regularized personalized PageRank can be solved in running time without depending on the size of the whole graph.

    ADAPTATION OF SCAN ORDER FOR ENTROPY CODING
    20.
    发明申请
    ADAPTATION OF SCAN ORDER FOR ENTROPY CODING 有权

    公开(公告)号：US20230123355A1

    公开(公告)日：2023-04-20

    申请号：US18084719

    申请日：2022-12-20

    Applicant: GOOGLE LLC

    Inventor： Dake He

    IPC: H04N19/129 ,  H04N19/18 ,  H04N19/172 ,  H04N19/176 ,  H04N19/182 ,  H04N19/61

    Abstract: Decoding a current block includes decoding a subset of quantized transform coefficients of a quantized transform block using a first scan order. A second scan order is determined based on the subset of the quantized transform coefficients. Remaining quantized transform coefficients of the quantized transform block are decoded based on the second scan order. A context model for decoding an intra-prediction mode is determined based on at least the subset of the quantized transform coefficients. The intra-prediction mode is decoded based on the context model. The current block is obtained based on the quantized transform coefficients and the intra-prediction mode.

Patent Agency Ranking