中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.035 seconds)

    Processing images using deep neural networks
    1.
    发明授权
    Processing images using deep neural networks 有权

    公开(公告)号：US09904875B2

    公开(公告)日：2018-02-27

    申请号：US15649947

    申请日：2017-07-14

    Applicant: Google Inc.

    Inventor： Christian Szegedy ,  Vincent O. Vanhoucke

    IPC: G06K9/46 ,  G06K9/66 ,  G06N3/04 ,  G06N3/08

    CPC classification number: G06K9/66 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/084

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

    IMAGE CLASSIFICATION NEURAL NETWORKS
    3.
    发明申请
    IMAGE CLASSIFICATION NEURAL NETWORKS 审中-公开

    公开(公告)号：US20170243085A1

    公开(公告)日：2017-08-24

    申请号：US15395530

    申请日：2016-12-30

    Applicant: Google Inc.

    Inventor： Vincent O. Vanhoucke ,  Christian Szegedy ,  Sergey Ioffe

    IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

    CPC classification number: G06K9/6267 ,  G06K9/00979 ,  G06K9/4628 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/08

    Abstract: A neural network system that includes: multiple subnetworks that includes: a first subnetwork including multiple first modules, each first module including: a pass-through convolutional layer configured to process the subnetwork input for the first subnetwork to generate a pass-through output; an average pooling stack of neural network layers that collectively processes the subnetwork input for the first subnetwork to generate an average pooling output; a first stack of convolutional neural network layers configured to collectively process the subnetwork input for the first subnetwork to generate a first stack output; a second stack of convolutional neural network layers that are configured to collectively process the subnetwork input for the first subnetwork to generate a second stack output; and a concatenation layer configured to concatenate the pass-through output, the average pooling output, the first stack output, and the second stack output to generate a first module output for the first module.

    System And Method For Displaying Contextual Supplemental Content Based On Image Content
    6.
    发明申请
    System And Method For Displaying Contextual Supplemental Content Based On Image Content 有权
    基于图像内容显示上下文补充内容的系统和方法

    公开(公告)号：US20150227813A1

    公开(公告)日：2015-08-13

    申请号：US14697190

    申请日：2015-04-27

    Applicant: Google Inc.

    Inventor： Vincent O. Vanhoucke ,  Salih Burak Gokturk ,  Munjal Shah ,  Julie Baumgartner

    IPC: G06K9/62 ,  G06Q30/02 ,  G06T7/00

    CPC classification number: G06K9/62 ,  G06K9/6267 ,  G06Q30/02 ,  G06Q30/0251 ,  G06T7/00

    Abstract: An image-based content item is analyzed to determine one or more interests of a viewer of the content item. The analysis may include performing image analysis on the content item to determine geographic information that is relevant to an image of the content item. The one or more interests may be determined based on an assumption or probabilistic conclusion about a subject of the content item. Further, the one or more interests may be determined by applying one or more rules that utilize the geographic information. For some embodiments, a supplemental content item may be provided to the viewer based on the one or more interests.

    Abstract translation: 分析基于图像的内容项目以确定内容项目的观看者的一个或多个兴趣。 分析可以包括对内容项进行图像分析以确定与内容项的图像相关的地理信息。 可以基于关于内容项目的主题的假设或概率结论来确定一个或多个兴趣。 此外，可以通过应用利用地理信息的一个或多个规则来确定一个或多个兴趣。 对于一些实施例，可以基于一个或多个兴趣向观看者提供补充内容项目。

    Speech recognition process
    7.
    发明授权
    Speech recognition process 有权
    语音识别过程

    公开(公告)号：US08775177B1

    公开(公告)日：2014-07-08

    申请号：US13665245

    申请日：2012-10-31

    Applicant: Google Inc.

    Inventor： Georg Heigold ,  Patrick An Phu Nguyen ,  Mitchel Weintraub ,  Vincent O. Vanhoucke

    IPC: G10L15/06

    CPC classification number: G10L15/10 ,  G10L2015/085

    Abstract: A speech recognition process may perform the following operations: performing a preliminary recognition process on first audio to identify candidates for the first audio; generating first templates corresponding to the first audio, where each first template includes a number of elements; selecting second templates corresponding to the candidates, where the second templates represent second audio, and where each second template includes elements that correspond to the elements in the first templates; comparing the first templates to the second templates, where comparing comprises includes similarity metrics between the first templates and corresponding second templates; applying weights to the similarity metrics to produce weighted similarity metrics, where the weights are associated with corresponding second templates; and using the weighted similarity metrics to determine whether the first audio corresponds to the second audio.

    Abstract translation: 语音识别处理可以执行以下操作：对第一音频执行初步识别处理以识别第一音频的候选; 生成与第一音频相对应的第一模板，其中每个第一模板包括多个元素; 选择与候选对应的第二模板，其中第二模板表示第二音频，并且其中每个第二模板包括与第一模板中的元素相对应的元素; 将第一模板与第二模板进行比较，其中比较包括第一模板与对应的第二模板之间的相似性度量; 对所述相似性度量应用权重以产生加权相似性度量，其中所述权重与相应的第二模板相关联; 以及使用所述加权相似性度量来确定所述第一音频是否对应于所述第二音频。

    PROCESSING IMAGES USING DEEP NEURAL NETWORKS
    8.
    发明申请
    PROCESSING IMAGES USING DEEP NEURAL NETWORKS 有权

    公开(公告)号：US20170316286A1

    公开(公告)日：2017-11-02

    申请号：US15649947

    申请日：2017-07-14

    Applicant: Google Inc.

    Inventor： Christian Szegedy ,  Vincent O. Vanhoucke

    IPC: G06K9/66 ,  G06N3/08 ,  G06N3/04

    CPC classification number: G06K9/66 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/084

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

    Processing images using deep neural networks
    9.
    发明授权
    Processing images using deep neural networks 有权

    公开(公告)号：US09715642B2

    公开(公告)日：2017-07-25

    申请号：US14839452

    申请日：2015-08-28

    Applicant: Google Inc.

    Inventor： Christian Szegedy ,  Vincent O. Vanhoucke

    IPC: G06K9/46 ,  G06K9/66 ,  G06N3/04 ,  G06N3/08

    CPC classification number: G06K9/66 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/084

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for image processing using deep neural networks. One of the methods includes receiving data characterizing an input image; processing the data characterizing the input image using a deep neural network to generate an alternative representation of the input image, wherein the deep neural network comprises a plurality of subnetworks, wherein the subnetworks are arranged in a sequence from lowest to highest, and wherein processing the data characterizing the input image using the deep neural network comprises processing the data through each of the subnetworks in the sequence; and processing the alternative representation of the input image through an output layer to generate an output from the input image.

Patent Agency Ranking