利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

98 条记录 (耗时 0.041 秒)

    Effective feature classification in images
    61.
    发明授权
    Effective feature classification in images 失效
    图像中的有效特征分类

    公开(公告)号：US08315465B1

    公开(公告)日：2012-11-20

    申请号：US12651128

    申请日：2009-12-31

    申请人： Shumeet Baluja ,  Michele Covell

    发明人： Shumeet Baluja ,  Michele Covell

    IPC分类号： G06K9/62

    CPC分类号： G06K9/6257 ,  G06K9/00456

    摘要： In general, the subject matter described in this specification can be embodied in methods, systems, and program products. A plurality of electronic training images that are each classified as displaying substantially pictures is obtained. A plurality of local image features in each of the plurality of electronic training images is identified. A plurality of weak classifiers are recursively applied to the local image features. During each iteration a weak classifier that accurately classifies the local images features is selected. After each selection of a weak classifier features that were misclassified by the selected weak classifier are given greater weight than features that were classified correctly by the selected weak classifier. For each selected weak classifier a hillclimbing algorithm is performed to attempt to improve the weak classifier. A strong classifier that is a weighted combination of the selected weak classifiers on which hillclimbing algorithms have been performed is produced.

    摘要翻译： 通常，本说明书中描述的主题可以体现在方法，系统和程序产品中。 获得被分类为基本上显示图像的多个电子训练图像。 识别多个电子训练图像中的每一个中的多个局部图像特征。 多个弱分类器递归地应用于局部图像特征。 在每次迭代期间，选择精确分类局部图像特征的弱分类器。 在选择的弱分类器被错误分类的弱分类器特征的每个选择之后，被赋予比选择的弱分类器正确分类的特征更大的权重。 对于每个选定的弱分类器，执行山坡计算以尝试改进弱分类器。 一种强分类器，它是已经执行了山地爬坡算法的所选弱分类器的加权组合。

    Detection and classification of matches between time-based media
    62.
    发明授权
    Detection and classification of matches between time-based media 有权
    基于时间的媒体之间的匹配检测和分类

    公开(公告)号：US08238669B2

    公开(公告)日：2012-08-07

    申请号：US12174366

    申请日：2008-07-16

    申请人： Michele Covell ,  Jay Yagnik ,  Jeff Faust ,  Shumeet Baluja

    发明人： Michele Covell ,  Jay Yagnik ,  Jeff Faust ,  Shumeet Baluja

    IPC分类号： G06K9/62 ,  H04N7/10 ,  H04N7/025

    CPC分类号： G06K9/00758 ,  G06F17/30784

    摘要： A system and method detects matches between portions of video content. A matching module receives an input video fingerprint representing an input video and a set of reference fingerprints representing reference videos in a reference database. The matching module compares the reference fingerprints and input fingerprints to generate a list of candidate segments from the reference video set. Each candidate segment comprises a time-localized portion of a reference video that potentially matches the input video. A classifier is applied to each of the candidate segments to classify the segment as a matching segment or a non-matching segment. A result is then outputted identifying a matching portion of a reference video from the reference video set based on the segments classified as matches.

    摘要翻译： 系统和方法检测视频内容的部分之间的匹配。 匹配模块接收表示参考数据库中的参考视频的输入视频和一组参考指纹的输入视频指纹。 匹配模块比较参考指纹和输入指纹，以从参考视频集中生成候选片段的列表。 每个候选片段包括潜在地匹配输入视频的参考视频的时间局部化部分。 将分类器应用于每个候选片段以将片段分类为匹配片段或非匹配片段。 然后基于被分类为匹配的段，从参考视频集中输出标识参考视频的匹配部分的结果。

    Communication and collaboration system using rich media environments
    64.
    发明授权
    Communication and collaboration system using rich media environments 有权
    使用富媒体环境的通信和协作系统

    公开(公告)号：US07590941B2

    公开(公告)日：2009-09-15

    申请号：US10682542

    申请日：2003-10-09

    申请人： Susie J. Wee ,  Henry Harlyn Baker ,  Nina T. Bhatti ,  Michele Covell ,  Michael Harville

    发明人： Susie J. Wee ,  Henry Harlyn Baker ,  Nina T. Bhatti ,  Michele Covell ,  Michael Harville

    IPC分类号： G06F3/00 ,  G06F3/14

    CPC分类号： H04H60/33 ,  G06Q10/10 ,  H04N7/15

    摘要： A system that enables communication and collaboration among individuals using rich media environments. A system according to the present techniques includes a set of rich media environments each having a corresponding arrangement of sensing and rendering components for sensing of and rendering to a corresponding set of individuals. A system according to the present techniques includes an interest thread detector that uses the sensing and rendering components to detect formation of multiple communication interactions among the individuals and that creates an interest thread for each detected communication interaction and further includes a communication provider that for each interest thread captures a set of media data from a corresponding subset of the sensing components and that combines the captured media data in response to the activities of the corresponding individuals and that communicates the combined media data to a corresponding subset of the rendering components.

    摘要翻译： 一个使用富媒体环境的个人之间进行通信和协作的系统。 根据本技术的系统包括一组富媒体环境，每个富媒体环境具有用于感测和呈现给对应的个体集合的感测和渲染组件的相应布置。 根据本技术的系统包括利益线程检测器，其利用感测和渲染组件来检测个体之间的多个通信交互的形成，并为每个检测到的通信交互创建兴趣线程，并且还包括针对每个兴趣的通信提供者 线程从感测组件的相应子集捕获一组媒体数据，并且响应于相应个体的活动而组合所捕获的媒体数据，并将组合的媒体数据传送到呈现组件的相应子集。

    Time-scale modification of data-compressed audio information
    65.
    发明申请
    Time-scale modification of data-compressed audio information 有权
    数据压缩音频信息的时间尺度修改

    公开(公告)号：US20070033057A1

    公开(公告)日：2007-02-08

    申请号：US11580559

    申请日：2006-10-12

    申请人： Michele Covell ,  Malcolm Slaney ,  Arthur Rothstein

    发明人： Michele Covell ,  Malcolm Slaney ,  Arthur Rothstein

    IPC分类号： G10L21/04

    CPC分类号： G10L21/04 ,  G10L19/173

    摘要： A data-compressed audio waveform is temporally modified without requiring complete decompression of the audio signal. Packets of compressed audio data are first unpacked, to remove scaling that was applied in the formation of the packets. The unpacked data is then temporally modified, using one of a number of different approaches. This modification takes place while the audio information remains in a data-compressed format. New packets are then assembled from the modified data, to produce a data-compressed output stream that can be subsequently processed in a conventional manner to reproduce the desired sound. The assembly of the new packets employs a technique for inferring an auditory model from the original packets, to requantize the data in the output packets.

    摘要翻译： 数据压缩音频波形在时间上被修改，而不需要音频信号的完全解压缩。 压缩音频数据的数据包首先被打包，以消除在数据包的形成中应用的缩放。 然后使用多种不同的方法之一来暂时地修改解包的数据。 当音频信息保持数据压缩格式时，进行这种修改。 然后从修改的数据组装新的分组，以产生可以以常规方式随后处理以再现期望的声音的数据压缩输出流。 新分组的组合采用从原始分组推断听觉模型的技术，以重新输出输出分组中的数据。

    Generating Human-Centric Directions in Mapping Systems
    66.
    发明申请
    Generating Human-Centric Directions in Mapping Systems 有权
    在映射系统中生成以人为本的方向

    公开(公告)号：US20070016368A1

    公开(公告)日：2007-01-18

    申请号：US11466326

    申请日：2006-08-22

    申请人： Charles Chapin ,  Michele Covell ,  Tiruvilwamalai Raman ,  Andrew Golding ,  Jens Rasmussen

    发明人： Charles Chapin ,  Michele Covell ,  Tiruvilwamalai Raman ,  Andrew Golding ,  Jens Rasmussen

    IPC分类号： G01C21/00

    CPC分类号： G01C21/3602 ,  G01C21/3644 ,  G01C21/3647

    摘要： Digital mapping techniques are disclosed that provide visually-oriented information to the user, such as driving directions that include visual data points along the way of the driving route, thereby improving the user experience. The user may preview the route associated with the driving directions, where the preview is based on, for example, at least one of satellite images, storefront images, and heuristics and/or business listings. The visually-oriented information can be presented to the user in a textual, graphical, or verbal format, or some combination thereof.

    摘要翻译： 公开了向用户提供面向视觉信息的数字映射技术，例如包括沿着驾驶路线的视觉数据点的行驶方向，从而改善用户体验。 用户可以预览与驾驶方向相关联的路线，其中预览基于例如卫星图像，店面图像和启发式和/或商业列表中的至少一个。 面向视觉的信息可以以文本，图形或语言格式或其某种组合呈现给用户。

    Method and system for improving the fidelity of a dialog system
    68.
    发明申请
    Method and system for improving the fidelity of a dialog system 有权

    公开(公告)号：US20060080102A1

    公开(公告)日：2006-04-13

    申请号：US10965540

    申请日：2004-10-13

    申请人： Sumit Roy ,  Michael Harville ,  Michele Covell

    发明人： Sumit Roy ,  Michael Harville ,  Michele Covell

    IPC分类号： G10L13/00

    CPC分类号： G10L13/08 ,  G10L15/065

    摘要： Embodiments of the present invention recite a method and system for improving the fidelity of a dialog system. In one embodiment, a first input generated by a user of a first system operating in a first modality is accessed. In embodiments of the present invention, the first system also generates a first output corresponding to the first input. An second input from a second user, who is engaged in a conversation with the first user, is accessed by a second system. The second input is then utilized to modify the first output of the first system.

    Time-scale modification of data-compressed audio information
    69.
    发明申请
    Time-scale modification of data-compressed audio information 有权

    公开(公告)号：US20050131683A1

    公开(公告)日：2005-06-16

    申请号：US10944456

    申请日：2004-09-17

    申请人： Michele Covell ,  Malcolm Slaney ,  Arthur Rothstein

    发明人： Michele Covell ,  Malcolm Slaney ,  Arthur Rothstein

    IPC分类号： G10L21/04 ,  G10L19/00

    CPC分类号： G11B20/00007 ,  G10L21/04 ,  G11B20/10527

    摘要： A data-compressed audio waveform is temporally modified without requiring complete decompression of the audio signal. Packets of compressed audio data are first unpacked, to remove scaling that was applied in the formation of the packets. The unpacked data is then temporally modified, using one of a number of different approaches. This modification takes place while the audio information remains in a data-compressed format. New packets are then assembled from the modified data, to produce a data-compressed output stream that can be subsequently processed in a conventional manner to reproduce the desired sound. The assembly of the new packets employs a technique for inferring an auditory model from the original packets, to requantize the data in the output packets.