中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

109 records (took 0.024 seconds)

    NETWORK REPARAMETERIZATION FOR NEW CLASS CATEGORIZATION
    31.
    发明申请
    NETWORK REPARAMETERIZATION FOR NEW CLASS CATEGORIZATION 审中-公开

    公开(公告)号：US20200097757A1

    公开(公告)日：2020-03-26

    申请号：US16580199

    申请日：2019-09-24

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Kai Li ,  Bing Bai ,  Hans Peter Graf

    IPC: G06K9/62 ,  G06K9/46 ,  G06N3/08

    Abstract: A computer-implemented method and system are provided for training a model for New Class Categorization (NCC) of a test image. The method includes decoupling, by a hardware processor, a feature extraction part from a classifier part of a deep classification model by reparametrizing learnable weight variables of the classifier part as a combination of learnable variables of the feature extraction part and of a classification weight generator of the classifier part. The method further includes training, by the hardware processor, the deep classification model to obtain a trained deep classification model by (i) learning the feature extraction part as a multiclass classification task, and (ii) episodically training the classifier part by learning a classification weight generator which outputs classification weights given a training image.

    Deep 3D attention long short-term memory for video-based action recognition
    36.
    发明授权
    Deep 3D attention long short-term memory for video-based action recognition 有权

    公开(公告)号：US10296793B2

    公开(公告)日：2019-05-21

    申请号：US15479408

    申请日：2017-04-05

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Yang Gao ,  Eric Cosatto

    IPC: G06K9/00 ,  G06N3/04 ,  G08B13/196 ,  H04N5/77 ,  H04N7/18 ,  G06K9/46 ,  G06K9/62

    Abstract: A method, a computer program product, and a system are provided for video based action recognition. The system includes a processor. One or more frames from one or more video sequences are received. A feature vector for each patch of the one or more frames is generated using a deep convolutional neural network. An attention factor for the feature vectors is generated based on a within-frame attention and a between-frame attention. A target action is identified using a multi-layer deep long short-term memory process applied to the attention factor, said target action representing at least one of the one or more video sequences. An operation of a processor-based machine is controlled to change a state of the processor-based machine, responsive to the at least one of the one or more video sequences including the identified target action.

    WORD EMBEDDING SYSTEM
    37.
    发明申请
    WORD EMBEDDING SYSTEM 审中-公开

    公开(公告)号：US20190122655A1

    公开(公告)日：2019-04-25

    申请号：US16163988

    申请日：2018-10-18

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Dinghan Shen

    IPC: G10L15/18 ,  G06N3/04 ,  G06N3/08 ,  G10L15/16 ,  G10L15/22 ,  G10L15/06

    Abstract: A computer-implemented method, computer program product, and computer processing system are provided for word embedding. The method includes receiving, by a processor device, a word embedding matrix. The method further includes generating, by a processor device, an average pooling vector and a max pooling vector, based on the word embedding matrix. The method also includes generating, by the processor device, a prediction by applying a Multi-Layer Perceptron (MLP) to the average pooling vector and the max pooling vector.

    Sparse higher-order Markov random field
    40.
    发明授权
    Sparse higher-order Markov random field 有权
    稀疏高阶马尔可夫随机场

    公开(公告)号：US09183503B2

    公开(公告)日：2015-11-10

    申请号：US13908715

    申请日：2013-06-03

    Applicant: NEC Laboratories America, Inc.

    Inventor： Renqiang Min ,  Yanjun Qi

    IPC: G06N5/02

    CPC classification number: G06N5/025

    Abstract: Systems and methods are provided for identifying combinatorial feature interactions, including capturing statistical dependencies between categorical variables, with the statistical dependencies being stored in a computer readable storage medium. A model is selected based on the statistical dependencies using a neighborhood estimation strategy, with the neighborhood estimation strategy including generating sets of arbitrarily high-order feature interactions using at least one rule forest and optimizing one or more likelihood functions. A damped mean-field approach is applied to the model to obtain parameters of a Markov random field (MRF); a sparse high-order semi-restricted MRF is produced by adding a hidden layer to the MRF; indirect long-range dependencies between feature groups are modeled using the sparse high-order semi-restricted MRF; and a combinatorial dependency structure between variables is output.

    Abstract translation: 提供了用于识别组合特征交互的系统和方法，包括捕获分类变量之间的统计依赖性，并将统计依赖性存储在计算机可读存储介质中。 基于使用邻域估计策略的统计依赖性来选择模型，邻域估计策略包括使用至少一个规则林生成任意高阶特征交互的集合并且优化一个或多个似然函数。 将阻尼平均场方法应用于模型以获得马尔可夫随机场（MRF）的参数; 通过向MRF添加隐藏层来产生稀疏高阶半限制MRF; 特征组之间的间接长程依赖关系使用稀疏高阶半限制MRF进行建模; 并输出变量之间的组合依赖结构。

Patent Agency Ranking