公开(公告)号：US06188776B1

公开(公告)日：2001-02-13

申请号：US08651108

申请日：1996-05-21

申请人： Michele Covell ,  Christoph Bregler

发明人： Michele Covell ,  Christoph Bregler

IPC分类号： G06K900

CPC分类号： G06K9/00281 ,  G06K9/4609 ,  G06K9/48 ,  G06K9/6211 ,  G06K2009/487

摘要： The identification of hidden data, such as feature-based control points in an image, from a set of observable data, such as the image, is achieved through a two-stage approach. The first stage involves a learning process, in which a number of sample data sets, e.g. images, are analyzed to identify the correspondence between observable data, such as visual aspects of the image, and the desired hidden data, such as the control points. Two models are created. A feature appearance-only model is created from aligned examples of the feature in the observed data. In addition, each labeled data set is processed to generate a coupled model of the aligned observed data and the associated hidden data. In the image processing embodiment, these two models might be affine manifold models of an object's appearance and of the coupling between that appearance and a set of locations on the object's surface. In the second stage of the process, the modeled feature is located in an unmarked, unaligned data set, using the feature appearance-only model. This location is used as an alignment point and the coupled model is then applied to the aligned data, giving an estimate of the hidden data values for that data set. In the image processing example, the object's appearance model is compared to different image locations. The matching locations are then used as alignment points for estimating the locations on the object's surface from the appearance in that aligned image and form the coupled model.

摘要翻译： 通过两阶段方法，可以从一组可观察数据（如图像）中识别隐藏数据，如图像中基于特征的控制点。 第一阶段涉及学习过程，其中多个样本数据集，例如， 分析图像以识别诸如图像的视觉方面的可观察数据与期望的隐藏数据（例如控制点）之间的对应关系。 创建了两个模型。 仅从观察数据中的特征的对齐示例创建仅出现特征的模型。 此外，处理每个标记的数据集以生成对准的观察数据和相关联的隐藏数据的耦合模型。 在图像处理实施例中，这两个模型可以是对象的外观和该外观与物体表面上的一组位置之间的耦合的仿射歧管模型。 在该过程的第二阶段，建模特征位于未标记的未对齐数据集中，使用仅特征外观模型。 该位置用作对齐点，然后将耦合模型应用于对齐的数据，给出该数据集的隐藏数据值的估计。 在图像处理示例中，将对象的外观模型与不同的图像位置进行比较。 然后将匹配位置用作对准点，以从该对准图像中的外观估计对象表面上的位置并形成耦合模型。

公开(公告)号：US20150371269A1

公开(公告)日：2015-12-24

申请号：US13598929

申请日：2012-08-30

申请人： Rohan Seth ,  Joshua J. Sacks ,  Michele Covell ,  Michael Chu ,  David Marwood ,  Shumeet Baluja

发明人： Rohan Seth ,  Joshua J. Sacks ,  Michele Covell ,  Michael Chu ,  David Marwood ,  Shumeet Baluja

IPC分类号： G06Q30/02 ,  G06F17/30

CPC分类号： G06Q30/0261 ,  G06F16/9537

摘要： Methods, system, and apparatus, including computer programs are encoded on a computer storage medium, for providing content based on geographic location data. In one aspect, a method includes receiving a request from a website for a map segment corresponding to a particular location. Keywords are extracted from the website as targeting criteria for the particular location. The targeting criteria is associated with the particular location. A subsequent request for advertising content associated with the particular location is received. One or more advertising content items are selected based on the targeting criteria. The selected advertising content items are provided responsive to the subsequent request.

摘要翻译： 包括计算机程序的方法，系统和装置在计算机存储介质上编码，用于基于地理位置数据提供内容。 一方面，一种方法包括从网站接收对应于特定位置的地图段的请求。 将关键字从网站提取为特定位置的定位条件。 定位条件与特定位置相关联。 接收与特定位置相关联的广告内容的后续请求。 基于目标标准来选择一个或多个广告内容项目。 响应于后续请求提供所选择的广告内容项目。

公开(公告)号：US08947595B1

公开(公告)日：2015-02-03

申请号：US12963901

申请日：2010-12-09

申请人： Richard Tucker ,  Henrik Rydgard ,  Gheorghe Postelnicu ,  Jasmine Kent ,  Michele Covell ,  Sergey Ioffe

发明人： Richard Tucker ,  Henrik Rydgard ,  Gheorghe Postelnicu ,  Jasmine Kent ,  Michele Covell ,  Sergey Ioffe

IPC分类号： H04N7/01 ,  H04N11/20 ,  H04N9/80 ,  G06F7/04 ,  G06F17/30 ,  H04N7/16 ,  G06K9/00

CPC分类号： H04N21/8352 ,  G06K9/00744 ,  H04N7/01 ,  H04N21/231 ,  H04N21/23418 ,  H04N21/26603 ,  H04N21/2743

摘要： A combined fingerprint is generated for a video that can match two near-identical videos that differ only in their aspect ratios or formats. A transformation strategy is selected by selecting a first and a second aspect correction method. A first transformed video is generated by applying the first aspect correction method to the video. A second transformed video is generated by applying the second aspect correction method to the video. A first fingerprint is generated using the first transformed video. A second fingerprint is generated using the second transformed video. The combined fingerprint is generated by combining the first half of the first fingerprint with the second half of the second fingerprint.

摘要翻译： 为视频生成组合指纹，该视频可以匹配两个仅在其长宽比或格式上不同的近似相同的视频。 通过选择第一和第二方面校正方法来选择变换策略。 通过将第一方面校正方法应用于视频来生成第一变换视频。 通过对视频应用第二方面校正方法来生成第二变换视频。 使用第一变换视频生成第一指纹。 使用第二变换视频生成第二指纹。 通过组合第一指纹的前半部分与第二指纹的后半部分来生成组合指纹。

公开(公告)号：US08909631B1

公开(公告)日：2014-12-09

申请号：US13217605

申请日：2011-08-25

申请人： Rohan Seth ,  Joshua J. Sacks ,  Michele Covell ,  Michael Chu ,  Shumeet Baluja ,  David Marwood

发明人： Rohan Seth ,  Joshua J. Sacks ,  Michele Covell ,  Michael Chu ,  Shumeet Baluja ,  David Marwood

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/3087 ,  G06Q30/02

摘要： Methods, systems, and computer program products, including computer programs encoded on a computer readable storage medium, for providing content to a user based on the mode of the user. A method includes: providing a data structure that includes query logs; processing query logs to determine candidate queries that satisfy a criteria, the processing including determining a location of interest, if any, for each query log entry and where the criteria requires an entry to have been submitted from a location that is different from a location of interest associated with the entry; evaluating the candidate queries to determine targeting information for the location of interest; receiving a request for content from a user that is proximate to the location of interest or has expressed an interest in the location of interest; and providing content to the user based at least in part on the targeting information.

摘要翻译： 方法，系统和计算机程序产品，包括在计算机可读存储介质上编码的计算机程序，用于基于用户的模式向用户提供内容。 一种方法包括：提供包括查询日志的数据结构; 处理查询日志以确定满足条件的候选查询，所述处理包括为每个查询日志条目确定感兴趣的位置（如果有的话），并且其中标准要求从不同于位置的位置提交条目 与入场有关的利息; 评估候选查询以确定感兴趣的位置的目标信息; 接收来自接近感兴趣位置的用户的内容请求，或者对感兴趣的位置表示兴趣; 以及至少部分地基于所述目标信息向所述用户提供内容。

公开(公告)号：US08732153B1

公开(公告)日：2014-05-20

申请号：US13616893

申请日：2012-09-14

申请人： Shumeet Baluja ,  Michele Covell

发明人： Shumeet Baluja ,  Michele Covell

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30646 ,  G06F17/30259 ,  G06F17/30864

摘要： A method includes receiving search queries. Images are generated that represent the volume of each search query relative to all search queries over a period of time. The images are processed to generate wavelets for each image. Related queries having similar increases or decreases in volume are identified by comparing at least some of the wavelets corresponding to a first query to wavelets corresponding to other queries.

摘要翻译： 一种方法包括接收搜索查询。 生成表示在一段时间内相对于所有搜索查询的每个搜索查询的卷的图像。 处理图像以生成每个图像的小波。 通过将对应于第一查询的至少一些小波与对应于其他查询的小波进行比较来识别具有类似体积增加或减小的相关查询。

公开(公告)号：US08515935B1

公开(公告)日：2013-08-20

申请号：US13219076

申请日：2011-08-26

申请人： Shumeet Baluja ,  Michele Covell

发明人： Shumeet Baluja ,  Michele Covell

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30646 ,  G06F17/30259 ,  G06F17/30864

摘要： A method includes receiving search queries. Images are generated that represent the volume of each search query relative to all search queries over a period of time. The images are processed to generate wavelets for each image. Related queries having similar increases or decreases in volume are identified by comparing at least some of the wavelets corresponding to a first query to wavelets corresponding to other queries.

摘要翻译： 一种方法包括接收搜索查询。 生成表示在一段时间内相对于所有搜索查询的每个搜索查询的卷的图像。 处理图像以生成每个图像的小波。 通过将对应于第一查询的至少一些小波与对应于其他查询的小波进行比较来识别具有类似体积增加或减小的相关查询。

公开(公告)号：US08498951B1

公开(公告)日：2013-07-30

申请号：US13250161

申请日：2011-09-30

申请人： Shumeet Baluja ,  Michele Covell

发明人： Shumeet Baluja ,  Michele Covell

IPC分类号： G06F15/18

CPC分类号： G06N3/08

摘要： A method including training a plurality of learning systems, each learning system implementing a learning function and having an input and producing an output, initializing one or more data structures, and evaluating a target sample is described. Also described are methods that include initializing one or more data structures and evaluating a target sample for a best match.

摘要翻译： 描述了一种训练多个学习系统的方法，每个学习系统实现学习功能并具有输入和产生输出，初始化一个或多个数据结构以及评估目标样本。 还描述了包括初始化一个或多个数据结构并评估目标样本以获得最佳匹配的方法。

公开(公告)号：US08184953B1

公开(公告)日：2012-05-22

申请号：US12391153

申请日：2009-02-23

申请人： Michele Covell ,  Sergey Ioffe ,  Shumeet Baluja ,  David Marwood

发明人： Michele Covell ,  Sergey Ioffe ,  Shumeet Baluja ,  David Marwood

IPC分类号： H04N9/80

CPC分类号： G06F17/30858 ,  G11B27/28

摘要： Videos are received and indexed based on fingerprints generated for the videos, using lookup keys which correspond to sub portions of the reference fingerprints. Specifically, a set of lookup keys is selected such that the number of reference fingerprints such that the clumping associated with the associated each of the lookup keys is minimized. Clumping occurs when a number of reference identifiers associated with a lookup key exceeds a maximum value.

摘要翻译： 基于为视频生成的指纹，使用与参考指纹的子部分相对应的查找键来接收和索引视频。 具体地，选择一组查找键，使得参考指纹的数量使得与相关联的每个查找键相关联的聚集被最小化。 当与查找键相关联的多个参考标识符超过最大值时，会发生分组。

公开(公告)号：US07433327B2

公开(公告)日：2008-10-07

申请号：US10683718

申请日：2003-10-09

申请人： Michael Harville ,  Michele Covell ,  Donald O. Tanguay, Jr.

发明人： Michael Harville ,  Michele Covell ,  Donald O. Tanguay, Jr.

IPC分类号： H04L12/28 ,  H04L12/56

CPC分类号： H04N7/142 ,  H04N7/147 ,  H04N7/152

摘要： In one embodiment, the present invention recites a coordinating component for creating an enhanced representation of an ongoing event using inputs from a communication session established between a plurality of communication devices. A first input port receives a first input from a first of the plurality of communication devices. A second input port receives a second input from a second of the plurality of communication devices. The first of the plurality of communication devices and the second of the plurality of communication devices do not have a prior association. A generator for selectively combining the first input and the second input creates an enhanced representation of the ongoing event. The enhanced representation is then output from an output port.

摘要翻译： 在一个实施例中，本发明描述了使用来自在多个通信设备之间建立的通信会话的输入来创建正在进行的事件的增强表示的协调组件。 第一输入端口从多个通信设备中的第一个接收第一输入。 第二输入端口从多个通信设备中的第二个接收第二输入。 多个通信设备中的第一个和多个通信设备中的第二个不具有先前的关联。 用于选择性地组合第一输入和第二输入的发生器创建正在进行的事件的增强的表示。 然后从输出端口输出增强表示。

公开(公告)号：US20060168288A1

公开(公告)日：2006-07-27

申请号：US11016472

申请日：2004-12-16

申请人： Michele Covell ,  Beomjoo Seo ,  Sumit Roy ,  Mirjana Spasojevic ,  Leonidas Kontothanassis ,  Nina Bhatti

发明人： Michele Covell ,  Beomjoo Seo ,  Sumit Roy ,  Mirjana Spasojevic ,  Leonidas Kontothanassis ,  Nina Bhatti

IPC分类号： G06F15/16

CPC分类号： G06F11/3495 ,  G06F11/3414 ,  G06F11/3419 ,  G06F11/3423 ,  G06F11/3447 ,  G06F11/3457 ,  G06F2201/86 ,  G06F2201/88

摘要： Methods and systems thereof for monitoring the performance of a streaming media server are described. A quality-of-service criterion is accessed. A failure to satisfy the quality-of-service criterion during streaming of data from the server to a plurality of clients is identified without assembling the data at the plurality of clients.

摘要翻译： 描述了用于监视流媒体服务器的性能的方法和系统。 访问服务质量标准。 在不在多个客户端组装数据的情况下，识别出在从服务器到多个客户端的数据流传输期间不能满足服务质量标准。