中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.022 seconds)

    CONDITIONAL ADAPTATION NETWORK FOR IMAGE CLASSIFICATION
    11.
    发明申请
    CONDITIONAL ADAPTATION NETWORK FOR IMAGE CLASSIFICATION 审中-公开

    公开(公告)号：US20180253627A1

    公开(公告)日：2018-09-06

    申请号：US15450620

    申请日：2017-03-06

    Applicant: Xerox Corporation

    Inventor： Fabien Baradel ,  Boris Chidlovskii ,  Gabriela Csurka

    IPC: G06K9/62

    CPC classification number: G06K9/00624 ,  G06K9/4628 ,  G06K9/6262 ,  G06K9/6271

    Abstract: A method and apparatus for classifying an image. In one example, the method may include receiving one or more images associated with a source domain and one or more images associated with a target domain, identifying one or more source domain features based on the one or more images associated with the source domain, identifying one or more target domain features based on the one or more images associated with the target domain, training a conditional maximum mean discrepancy (CMMD) engine based on a difference between the one or more source domain features and the one or more target domain features, applying the CMMD engine to the one or more images associated with the target domain to generate one or more labels for each unlabeled target image of the one or more images associated with the target domain and classifying each one of the one or more images in the target domain using the one or more labels.

    ADAPTED DOMAIN SPECIFIC CLASS MEANS CLASSIFIER
    13.
    发明申请
    ADAPTED DOMAIN SPECIFIC CLASS MEANS CLASSIFIER 审中-公开

    公开(公告)号：US20170147944A1

    公开(公告)日：2017-05-25

    申请号：US14950544

    申请日：2015-11-24

    Applicant: Xerox Corporation

    Inventor： Gabriela Csurka ,  Boris Chidlovskii ,  Stéphane Clinchant

    IPC: G06N99/00 ,  G06N5/02

    CPC classification number: G06N99/005 ,  G06N3/0454 ,  G06N3/084 ,  G06N5/02

    Abstract: A domain-adapted classification system and method are disclosed. The method includes mapping an input set of representations to generate an output set of representations, using a learned transformation. The input set of representations includes a set of target samples from a target domain. The input set also includes, for each of a plurality of source domains, a class representation for each of a plurality of classes. The class representations are representative of a respective set of source samples from the respective source domain labeled with a respective class. The output set of representations includes an adapted representation of each of the target samples and an adapted class representation for each of the classes for each of the source domains. A class label is predicted for at least one of the target samples based on the output set of representations and information based on the predicted class label is output.

    Print path obfuscation method and system for document content analytics assessment
    14.
    发明授权
    Print path obfuscation method and system for document content analytics assessment 有权
    打印路径混淆方法和文档内容分析评估系统

    公开(公告)号：US09477913B2

    公开(公告)日：2016-10-25

    申请号：US14539492

    申请日：2014-11-12

    Applicant: Xerox Corporation

    Inventor： Gabriela Csurka ,  Jerome Pouyadou ,  Jutta Katharina Willamowski ,  Yves Hoppenot

    IPC: G06F3/12 ,  G06K15/02 ,  G06K15/00 ,  G06F17/22

    CPC classification number: G06K15/1867 ,  G06F17/22 ,  G06K15/4095

    Abstract: Disclosed is a method and system of differential processing a print job including one or more original documents to render an obfuscated version of the print job. According to an exemplary method, the differential process replaces letters of an original document with randomly selected characters of substantially the same size and location as the original document and objects such as images/graphics are replaced with blurred versions of substantially the same size and locations as the objects in the original document. The differential process creates an obfuscated version of the print job which is illegible and useful for further processing where privacy of documents included in the print job is required.

    Abstract translation: 公开了一种差分处理包括一个或多个原始文档以打印打印作业的混淆版本的打印作业的方法和系统。 根据示例性方法，差分过程用原始文档替换原始文档的字母与随机选择的大小和位置大小相同的字符，并且诸如图像/图形的对象被基本相同的尺寸和位置的模糊版本替换 原始文档中的对象。 差分过程创建了一个混淆版本的打印作业，对于需要打印作业中包含的文档隐私的进一步处理而言，这是不可辨识和有用的。

    TARGETED SUMMARIZATION OF MEDICAL DATA BASED ON IMPLICIT QUERIES
    15.
    发明申请
    TARGETED SUMMARIZATION OF MEDICAL DATA BASED ON IMPLICIT QUERIES 审中-公开
    基于隐含查询的医学数据目标概述

    公开(公告)号：US20140350961A1

    公开(公告)日：2014-11-27

    申请号：US13898805

    申请日：2013-05-21

    Applicant: Xerox Corporation

    Inventor： Gabriela Csurka ,  Mario Agustin Ricardo Jarmasz ,  Florent C. Perronnin ,  Juan Antonio Lossio Ventura

    IPC: G06F19/00

    CPC classification number: G16H10/60

    Abstract: A system and method for targeted summarization of a patient's electronic medical records are provided. The system includes an aggregation component which provides an aggregation of health records of a patient. A transformation component transforms the health records of the patient into representations in a multidimensional search space. A search component generates an implicit query in the multidimensional search space and retrieves responsive heath records based on the implicit query. A summarization component generates a summary based on the retrieved responsive health records for display to a healthcare provider on an associated user interface. A processor implements the aggregation component, transformation component, search component, and summarization component.

    Abstract translation: 提供了一种用于病人电子医疗记录的有针对性总结的系统和方法。 该系统包括聚合组件，其提供患者的健康记录的聚集。 转换组件将患者的健康记录转换为多维搜索空间中的表示。 搜索组件在多维搜索空间中生成隐式查询，并根据隐式查询检索响应的健康记录。 摘要组件基于检索的响应健康记录生成摘要，以在相关联的用户界面上向医疗保健提供者显示。 处理器实现聚合组件，转换组件，搜索组件和汇总组件。

    SYSTEM AND METHOD FOR MULTIMEDIA INFORMATION RETRIEVAL
    16.
    发明申请
    SYSTEM AND METHOD FOR MULTIMEDIA INFORMATION RETRIEVAL 审中-公开
    多媒体信息检索系统与方法

    公开(公告)号：US20130282687A1

    公开(公告)日：2013-10-24

    申请号：US13888667

    申请日：2013-05-07

    Applicant: Xerox Corporation

    Inventor： Julien Ah-Pine ,  Stephane Clinchant ,  Gabriela Csurka

    IPC: G06F17/30

    CPC classification number: G06F16/43 ,  G06F16/951 ,  G06F17/18 ,  G06K9/6293

    Abstract: A method for information retrieval includes querying a multimedia collection with a first component of a multimedia query to generate first comparison measures between the first component of the query and respective objects in the collection for a first media type. The collection is queried with a second component of the multimedia query to generate second comparison measures between the second component of the query and respective objects in the collection for a second media type. An aggregated score for each of a set of objects in the collection is computed by applying an aggregating function in which a first confidence weighting is applied to the first comparison measure and a second confidence weighting is applied to the second comparison measure. The first confidence weighting is independent of the second comparison measure. The second confidence weighting is dependent on the first comparison measure.

    Abstract translation: 一种用于信息检索的方法包括使用多媒体查询的第一分量来查询多媒体集合，以产生第一媒体类型的查询的第一个组件与集合中的相应对象之间的第一个比较度量。 使用多媒体查询的第二组件查询该集合，以生成查询的第二组件与第二媒体类型的集合中的相应对象之间的第二比较度量。 通过应用将第一置信加权应用于第一比较测量的聚合函数并且将第二置信加权应用于第二比较度量来计算集合中的一组对象中的每一个的聚合分数。 第一个置信权重与第二个比较度量无关。 第二个置信权重取决于第一个比较度量。

    Transductive adaptation of classifiers without source data
    17.
    发明授权
    Transductive adaptation of classifiers without source data 有权

    公开(公告)号：US10354199B2

    公开(公告)日：2019-07-16

    申请号：US14960869

    申请日：2015-12-07

    Applicant: Xerox Corporation

    Inventor： Stéphane Clinchant ,  Gabriela Csurka ,  Boris Chidlovskii

    IPC: G06N20/00 ,  G06N3/04

    Abstract: A classification method includes receiving a collection of samples, each sample comprising a multidimensional feature representation. A class label prediction for each sample in the collection is generated with one or more pretrained classifiers. For at least one iteration, each multidimensional feature representation is augmented with a respective class label prediction to form an augmented representation, a set of corrupted samples is generated from the augmented representations, and a transformation that minimizes a reconstruction error for the set of corrupted samples is learned. An adapted class label prediction for at least one of the samples in the collection is generated using the learned transformation and information is output, based on the adapted class label prediction. The method is useful in predicting labels for target samples where there is no access to source domain samples that are used to train the classifier and no access to target domain training data.

    Domain adaptation by multi-noising stacked marginalized denoising encoders
    18.
    发明授权
    Domain adaptation by multi-noising stacked marginalized denoising encoders 有权

    公开(公告)号：US09916542B2

    公开(公告)日：2018-03-13

    申请号：US15013273

    申请日：2016-02-02

    Applicant: Xerox Corporation

    Inventor： Boris Chidlovskii ,  Gabriela Csurka ,  Stéphane Clinchant

    IPC: G06N99/00 ,  G06K9/62 ,  G06K9/00

    CPC classification number: G06N99/005 ,  G06K9/00684 ,  G06K9/6256 ,  G06K9/6262 ,  G06K9/6298

    Abstract: A machine learning method operates on training instances from a plurality of domains including one or more source domains and a target domain. Each training instance is represented by values for a set of features. Domain adaptation is performed using stacked marginalized denoising autoencoding (mSDA) operating on the training instances to generate a stack of domain adaptation transform layers. Each iteration of the domain adaptation includes corrupting the training instances in accord with feature corruption probabilities that are non-uniform over at least one of the set of features and the domains. A classifier is learned on the training instances transformed using the stack of domain adaptation transform layers. Thereafter, a label prediction is generated for an input instance from the target domain represented by values for the set of features by applying the classifier to the input instance transformed using the stack of domain adaptation transform domains.

    ADAPTING MULTIPLE SOURCE CLASSIFIERS IN A TARGET DOMAIN
    19.
    发明申请
    ADAPTING MULTIPLE SOURCE CLASSIFIERS IN A TARGET DOMAIN 审中-公开

    公开(公告)号：US20170220951A1

    公开(公告)日：2017-08-03

    申请号：US15013401

    申请日：2016-02-02

    Applicant: Xerox Corporation

    Inventor： Boris Chidlovskii ,  Gabriela Csurka ,  Stéphane Clinchant

    IPC: G06N99/00 ,  G06F17/27

    CPC classification number: G06N20/00 ,  G06F16/35

    Abstract: Training instances from a target domain are represented by feature vectors storing values for a set of features, and are labeled by labels from a set of labels. Both a noise marginalizing transform and a weighting of one or more source domain classifiers are simultaneously learned by minimizing the expectation of a loss function that is dependent on the feature vectors corrupted with noise represented by a noise probability density function, the labels, and the one or more source domain classifiers operating on the feature vectors corrupted with the noise. An input instance from the target domain is labeled with a label from the set of labels by operations including applying the learned noise marginalizing transform to an input feature vector representing the input instance and applying the one or more source domain classifiers weighted by the learned weighting to the input feature vector representing the input instance.

Patent Agency Ranking