利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

26 条记录 (耗时 0.019 秒)

    Training scoring models optimized for highly-ranked results
    2.
    发明授权
    Training scoring models optimized for highly-ranked results 失效

    公开(公告)号：US08429212B1

    公开(公告)日：2013-04-23

    申请号：US13342532

    申请日：2012-01-03

    申请人： Samy Bengio ,  Gal Chechik ,  Sergey Ioffe ,  Jay Yagnik

    发明人： Samy Bengio ,  Gal Chechik ,  Sergey Ioffe ,  Jay Yagnik

    IPC分类号： G06F17/00

    CPC分类号： G06K9/66 ,  G06F17/30244 ,  G06F17/3053 ,  G06K9/6267 ,  Y10S707/913 ,  Y10S707/915

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training scoring models. One method includes storing data identifying a plurality of positive and a plurality of negative training images for a query. The method further includes selecting a first image from either the positive group of images or the negative group of images, and applying a scoring model to the first image. The method further includes selecting a plurality of candidate images from the other group of images, applying the scoring model to each of the candidate images, and then selecting a second image from the candidate images according to scores for the images. The method further includes determining that the scores for the first image and the second image fail to satisfy a criterion, updating the scoring model, and storing the updated scoring model.

    Training scoring models optimized for highly-ranked results
    3.
    发明授权
    Training scoring models optimized for highly-ranked results 有权
    培训评分模型针对高排名结果进行了优化

    公开(公告)号：US08131786B1

    公开(公告)日：2012-03-06

    申请号：US12624001

    申请日：2009-11-23

    申请人： Samy Bengio ,  Gal Chechik ,  Sergey Ioffe ,  Jay Yagnik

    发明人： Samy Bengio ,  Gal Chechik ,  Sergey Ioffe ,  Jay Yagnik

    IPC分类号： G06F17/00

    CPC分类号： G06K9/66 ,  G06F17/30244 ,  G06F17/3053 ,  G06K9/6267 ,  Y10S707/913 ,  Y10S707/915

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training scoring models. One method includes storing data identifying a plurality of positive and a plurality of negative training images for a query. The method further includes selecting a first image from either the positive group of images or the negative group of images, and applying a scoring model to the first image. The method further includes selecting a plurality of candidate images from the other group of images, applying the scoring model to each of the candidate images, and then selecting a second image from the candidate images according to scores for the images. The method further includes determining that the scores for the first image and the second image fail to satisfy a criterion, updating the scoring model, and storing the updated scoring model.

    摘要翻译： 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，用于训练评分模型。 一种方法包括存储识别用于查询的多个正训练图像和多个负训练图像的数据。 该方法还包括从图像的正组或负图像组中选择第一图像，以及将评分模型应用于第一图像。 该方法还包括从另一组图像中选择多个候选图像，将评分模型应用于每个候选图像，然后根据图像的分数从候选图像中选择第二图像。 该方法还包括确定第一图像和第二图像的分数不能满足标准，更新评分模型，并存储更新的评分模型。

    Training scoring models optimized for highly-ranked results
    4.
    发明授权
    Training scoring models optimized for highly-ranked results 有权

    公开(公告)号：US08589457B1

    公开(公告)日：2013-11-19

    申请号：US13616108

    申请日：2012-09-14

    申请人： Samy Bengio ,  Gal Chechik ,  Sergey Ioffe ,  Jay Yagnik

    发明人： Samy Bengio ,  Gal Chechik ,  Sergey Ioffe ,  Jay Yagnik

    IPC分类号： G06F17/00

    CPC分类号： G06K9/66 ,  G06F17/30244 ,  G06F17/3053 ,  G06K9/6267 ,  Y10S707/913 ,  Y10S707/915

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training scoring models. One method includes storing data identifying a plurality of positive and a plurality of negative training images for a query. The method further includes selecting a first image from either the positive group of images or the negative group of images, and applying a scoring model to the first image. The method further includes selecting a plurality of candidate images from the other group of images, applying the scoring model to each of the candidate images, and then selecting a second image from the candidate images according to scores for the images. The method further includes determining that the scores for the first image and the second image fail to satisfy a criterion, updating the scoring model, and storing the updated scoring model.

    Audio classification for information retrieval using sparse features
    5.
    发明授权
    Audio classification for information retrieval using sparse features 有权
    使用稀疏特征进行信息检索的音频分类

    公开(公告)号：US08463719B2

    公开(公告)日：2013-06-11

    申请号：US12722437

    申请日：2010-03-11

    申请人： Richard F. Lyon ,  Martin Rehn ,  Thomas Walters ,  Samy Bengio ,  Gal Chechik

    发明人： Richard F. Lyon ,  Martin Rehn ,  Thomas Walters ,  Samy Bengio ,  Gal Chechik

    IPC分类号： G06F15/18

    CPC分类号： G10L25/48 ,  G06F17/30743

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, are provided for using audio features to classify audio for information retrieval. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of generating a collection of auditory images, each auditory image being generated from respective audio files according to an auditory model; extracting sparse features from each auditory image in the collection to generate a sparse feature vector representing the corresponding audio file; and ranking the audio files in response to a query including one or more words using the sparse feature vectors and a matching function relating sparse feature vectors to words in the query.

    摘要翻译： 提供方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于使用音频特征来分类用于信息检索的音频。 通常，本说明书中描述的主题的一个方面可以包括生成听觉图像的集合的动作的方法，每个听觉图像根据听觉模型从各个音频文件生成; 从集合中的每个听觉图像中提取稀疏特征以生成表示相应音频文件的稀疏特征向量; 以及响应于包括使用所述稀疏特征向量的一个或多个单词的查询和将稀疏特征向量与所述查询中的单词相关联的匹配函数进行排序。

    AUDIO CLASSIFICATION FOR INFORMATION RETRIEVAL USING SPARSE FEATURES
    6.
    发明申请
    AUDIO CLASSIFICATION FOR INFORMATION RETRIEVAL USING SPARSE FEATURES 有权
    使用稀疏特征的信息检索的音频分类

    公开(公告)号：US20100257129A1

    公开(公告)日：2010-10-07

    申请号：US12722437

    申请日：2010-03-11

    申请人： Robert F. Lyon ,  Martin Rehn ,  Thomas Walters ,  Samy Bengio ,  Gal Chechik

    发明人： Robert F. Lyon ,  Martin Rehn ,  Thomas Walters ,  Samy Bengio ,  Gal Chechik

    IPC分类号： G06F17/30 ,  G06F15/18

    CPC分类号： G10L25/48 ,  G06F17/30743

    摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, are provided for using audio features to classify audio for information retrieval. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of generating a collection of auditory images, each auditory image being generated from respective audio files according to an auditory model; extracting sparse features from each auditory image in the collection to generate a sparse feature vector representing the corresponding audio file; and ranking the audio files in response to a query including one or more words using the sparse feature vectors and a matching function relating sparse feature vectors to words in the query.

    摘要翻译： 提供方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于使用音频特征来分类用于信息检索的音频。 通常，本说明书中描述的主题的一个方面可以包括生成听觉图像的集合的动作的方法，每个听觉图像根据听觉模型从各个音频文件生成; 从集合中的每个听觉图像中提取稀疏特征以生成表示相应音频文件的稀疏特征向量; 以及响应于包括使用所述稀疏特征向量的一个或多个单词的查询和将稀疏特征向量与查询中的单词相关联的匹配函数进行排序。

    Relevance-Based Image Selection
    7.
    发明申请
    Relevance-Based Image Selection 审中-公开
    相关性图像选择

    公开(公告)号：US20110047163A1

    公开(公告)日：2011-02-24

    申请号：US12546436

    申请日：2009-08-24

    申请人： Gal Chechik ,  Samy Bengio

    发明人： Gal Chechik ,  Samy Bengio

    IPC分类号： G06F17/30

    CPC分类号： G06F16/7867 ,  G06F16/70 ,  G06F16/738 ,  G06F16/743 ,  G06F16/78 ,  G06F16/783

    摘要： A system, computer readable storage medium, and computer-implemented method presents video search results responsive to a user keyword query. The video hosting system uses a machine learning process to learn a feature-keyword model associating features of media content from a labeled training dataset with keywords descriptive of their content. The system uses the learned model to provide video search results relevant to a keyword query based on features found in the videos. Furthermore, the system determines and presents one or more thumbnail images representative of the video using the learned model.

    摘要翻译： 系统，计算机可读存储介质和计算机实现的方法响应于用户关键词查询呈现视频搜索结果。 视频托管系统使用机器学习过程来学习将标记训练数据集中的媒体内容的特征与描述其内容的关键字相关联的特征关键字模型。 该系统使用学习模型，根据视频中的功能提供与关键字查询相关的视频搜索结果。 此外，系统使用所学习的模型来确定并呈现代表视频的一个或多个缩略图。

    Process for the renewal--during communication--of the traffic parameters of an ATM network
    10.
    发明授权
    Process for the renewal--during communication--of the traffic parameters of an ATM network 失效
    在通信期间更新ATM网络的流量参数的过程

    公开(公告)号：US6018517A

    公开(公告)日：2000-01-25

    申请号：US803273

    申请日：1997-02-20

    申请人： Samy Bengio ,  Fabrice Clerot ,  Annie Gravey ,  Daniel Collobert

    发明人： Samy Bengio ,  Fabrice Clerot ,  Annie Gravey ,  Daniel Collobert

    IPC分类号： H04Q3/00 ,  H04L12/54 ,  H04L12/70 ,  G01R31/08 ,  G06F11/00 ,  G08C15/00 ,  H04J3/16

    CPC分类号： H04L12/5602 ,  H04L2012/5632 ,  H04L2012/5634

    摘要： A process for renegotiating, during a communication, the parameters of a traffic contract on an ATM network.The present invention relates to a renegotiation process, during a communication on an ATM network, of the parameters of the traffic contract that relates to this communication. It is characterized in that it consists:a. in predicting, for a predetermined period of time between two successive renegotiations, the maximal length that would be reached by a virtual file fed by the traffic of said communication, for at least a given thruput rate of said file.b. in deducing from said maximal length one or more new parameters for the traffic contract, andc. in renegotiating with the network on the basis of said (new) traffic parameter or parameters for said period of time.

    摘要翻译： 在通信期间重新谈判ATM网络上的交通合同的参数的过程。 本发明涉及一种在ATM网络上的通信过程中与该通信相关的交通合同的参数的重新协商过程。 它的特点是它包括：a。 在预测两次连续重新协商之间的预定时间段内，为所述文件的至少一个给定的猝发速率预测由所述通信的业务所馈送的虚拟文件将达到的最大长度。 b。 从所述最大长度推导出交通契约的一个或多个新参数，以及c。 在所述（新的）流量参数或所述时间段的参数的基础上与网络重新谈判。