中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.011 seconds)

    Hash Learning
    3.
    发明申请
    Hash Learning 审中-公开
    哈希学习

    公开(公告)号：US20150169682A1

    公开(公告)日：2015-06-18

    申请号：US14057007

    申请日：2013-10-18

    Applicant: Google Inc.

    Inventor： Alexander Toshkov Toshev

    IPC: G06F17/30

    CPC classification number: G06F16/9014 ,  G06F16/137

    Abstract: An asymmetric hashing system that hashes query and class labels onto the same space where queries can be hashed to the same binary codes as their labels. The assignment of the class labels to the hash space can be alternately optimized with the query hash function, resulting in an accurate system whose inference complexity that is sublinear to the number of classes. Queries such as image queries can be processed quickly and correctly.

    Abstract translation: 一个非对称散列系统，将查询和类标签散列到相同空间中，查询可以与其标签相同的二进制代码。 将类标签分配到散列空间可以与查询哈希函数进行交替优化，从而产生一个准确的系统，其推理复杂度与类数的次数相同。 可以快速正确地处理查询（如图像查询）。

    Ranking approach to train deep neural nets for multilabel image annotation
    4.
    发明授权
    Ranking approach to train deep neural nets for multilabel image annotation 有权
    对多标签图像注释训练深层神经网络的排名方法

    公开(公告)号：US09552549B1

    公开(公告)日：2017-01-24

    申请号：US14444272

    申请日：2014-07-28

    Applicant: Google Inc.

    Inventor： Yunchao Gong ,  King Hong Thomas Leung ,  Alexander Toshkov Toshev ,  Sergey Ioffe ,  Yangqing Jia

    IPC: G06N3/08

    CPC classification number: G06N3/084 ,  G06N3/0454

    Abstract: Systems and techniques are provided for a ranking approach to train deep neural nets for multilabel image annotation. Label scores may be received for labels determined by a neural network for training examples. Each label may be a positive label or a negative label for the training example. An error of the neural network may be determined based on a comparison, for each of the training examples, of the label scores for positive labels and negative labels for the training example and a semantic distance between each positive label and each negative label for the training example. Updated weights may be determined for the neural network based on a gradient of the determined error of the neural network. The updated weights may be applied to the neural network to train the neural network.

    Abstract translation: 提供系统和技术用于排列方法来训练用于多标签图像注释的深层神经网络。 可以接收由用于训练示例的神经网络确定的标签的标签分数。 每个标签可能是培训示例的正标签或负标签。 可以基于针对训练样本的正标签的标签分数和训练样本的负标签的每个训练样本的比较以及训练样本的每个正标签和每个负标签之间的语义距离来确定神经网络的误差 例。 可以基于确定的神经网络的误差的梯度来确定神经网络的更新权重。 更新的权重可以应用于神经网络来训练神经网络。

    GENERATING NATURAL LANGUAGE DESCRIPTIONS OF IMAGES
    5.
    发明申请
    GENERATING NATURAL LANGUAGE DESCRIPTIONS OF IMAGES 有权
    产生自然语言描述的图像

    公开(公告)号：US20160140435A1

    公开(公告)日：2016-05-19

    申请号：US14941454

    申请日：2015-11-13

    Applicant: Google Inc.

    Inventor： Samy Bengio ,  Oriol Vinyals ,  Alexander Toshkov Toshev ,  Dumitru Erhan

    IPC: G06N3/04 ,  G06F17/28

    CPC classification number: G06N3/0472 ,  G06F17/28 ,  G06N3/0454

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating descriptions of input images. One of the methods includes obtaining an input image; processing the input image using a first neural network to generate an alternative representation for the input image; and processing the alternative representation for the input image using a second neural network to generate a sequence of a plurality of words in a target natural language that describes the input image.

    Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于产生输入图像的描述。 方法之一包括获取输入图像; 使用第一神经网络处理所述输入图像以生成所述输入图像的替代表示; 以及使用第二神经网络处理所述输入图像的替代表示，以生成描述所述输入图像的目标自然语言中的多个单词的序列。

    Object detection using deep neural networks
    6.
    发明授权
    Object detection using deep neural networks 有权
    使用深层神经网络的对象检测

    公开(公告)号：US09275308B2

    公开(公告)日：2016-03-01

    申请号：US14288194

    申请日：2014-05-27

    Applicant: Google Inc.

    Inventor： Christian Szegedy ,  Dumitru Erhan ,  Alexander Toshkov Toshev

    IPC: G06K9/62 ,  G06K9/66

    CPC classification number: G06K9/66 ,  G06K9/4628

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting objects in images. One of the methods includes receiving an input image. A full object mask is generated by providing the input image to a first deep neural network object detector that produces a full object mask for an object of a particular object type depicted in the input image. A partial object mask is generated by providing the input image to a second deep neural network object detector that produces a partial object mask for a portion of the object of the particular object type depicted in the input image. A bounding box is determined for the object in the image using the full object mask and the partial object mask.

    Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于检测图像中的对象。 其中一种方法包括接收输入图像。 通过将输入图像提供给产生输入图像中描绘的特定对象类型的对象的完整对象掩模的第一深层神经网络对象检测器来生成完整对象掩码。 通过将输入图像提供给第二深神经网络对象检测器来产生部分对象掩模，该第二深神经网络对象检测器为输入图像中描绘的特定对象类型的对象的一部分产生部分对象掩模。 使用完整对象掩码和部分对象掩码，为图像中的对象确定边框。

    Sublinear time classification via feature padding and hashing
    7.
    发明授权
    Sublinear time classification via feature padding and hashing 有权
    通过特征填充和散列进行子线性时间分类

    公开(公告)号：US09286549B1

    公开(公告)日：2016-03-15

    申请号：US13941812

    申请日：2013-07-15

    Applicant: Google Inc.

    Inventor： Sergey Ioffe ,  Alexander Toshkov Toshev

    IPC: G06K9/68 ,  G06K9/70 ,  G06K9/62

    CPC classification number: G06K9/6276 ,  G06K9/6215 ,  G06K9/6267 ,  G06K9/628

    Abstract: A linear function describing a framework for identifying an object of class k in an image sample x may be described by: wk*x+bk, where bk is the bias term. The higher the value obtained for a particular classifier, the better the match or strength of identity. A method is disclosed for classifier and/or content padding to convert dot-products to distances, applying a hashing and/or nearest neighbor technique on the resulting padded vectors, and preprocessing that may improve the hash entropy. A vector for an image, an audio, and/or a video may be received. One or more classifier vectors may be obtained. A padded image, video, and/or audio vector and classifier vector may be generated. A dot product may be approximated and a hashing and/or nearest neighbor technique may be performed on the approximated dot product to identify at least one class (or object) present in the image, video, and/or audio.

    Abstract translation: 描述用于识别图像样本x中的类k的对象的框架的线性函数可以由以下描述：wk * x + bk，其中bk是偏差项。 特定分类器获得的值越高，身份的匹配或强度越好。 公开了一种用于分类器和/或内容填充以将点产品转换为距离的方法，在所得到的填充向量上应用散列和/或最近邻技术，以及可以改善散列熵的预处理。 可以接收用于图像，音频和/或视频的向量。 可以获得一个或多个分类器向量。 可以生成填充图像，视频和/或音频向量和分类器向量。 可以近似点积，并且可以在近似点积上执行散列和/或最近邻技术，以识别存在于图像，视频和/或音频中的至少一个类（或对象）。

    System and method for using segmentation to identify object location in images
    8.
    发明授权
    System and method for using segmentation to identify object location in images 有权

    公开(公告)号：US10061999B1

    公开(公告)日：2018-08-28

    申请号：US15339616

    申请日：2016-10-31

    Applicant: Google Inc.

    Inventor： Vivek Kwatra ,  Jay Yagnik ,  Alexander Toshkov Toshev

    IPC: G06K9/62 ,  G06K9/32 ,  G06T7/00

    CPC classification number: G06K9/3241 ,  G06K9/00771 ,  G06K9/468 ,  G06K9/6255 ,  G06T7/11 ,  G06T7/174 ,  G06T2207/20081

    Abstract: An example method is disclosed that includes identifying a training set of images, wherein each image in the training set has an identified bounding box that comprises an object class and an object location for an object in the image. The method also includes segmenting each image of the training set, wherein segments comprise sets of pixels that share visual characteristics, and wherein each segment is associated with an object class. The method further includes clustering the segments that are associated with the same object class, and generating a data structure based on the clustering, wherein entries in the data structure comprise visual characteristics for prototypical segments of objects having the object class and further comprise one or more potential bounding boxes for the objects, wherein the data structure is usable to predict bounding boxes of additional images that include an object having the object class.

Patent Agency Ranking