公开(公告)号：US08583567B1

公开(公告)日：2013-11-12

申请号：US13184014

申请日：2011-07-15

申请人： Sanjiv Kumar ,  Jun Wang

发明人： Sanjiv Kumar ,  Jun Wang

IPC分类号： G06F15/18

CPC分类号： G06N99/005 ,  H04L9/3236

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating hash functions. In one aspect, a method includes generating hash functions by sequentially determining a weight vector for each hash function to maximize an accuracy measure derived from current constraint weights and updating the current constraint weights for use in calculating a weight vector of a next hash function in the sequence. In another aspect, the determined weight vector maximizes an accuracy measure and a variance measure. In still another aspect, a method includes generating an adjusted covariance matrix and generating a sequence of hash functions from the adjusted covariance matrix. In still another aspect, a method includes sequentially generating a sequence of hash functions, where the weight vectors for any previously generated hash functions are used to identify constraints used to generate the weight vector for each next hash function in the sequence.

公开(公告)号：US08825563B1

公开(公告)日：2014-09-02

申请号：US13184013

申请日：2011-07-15

申请人： Sanjiv Kumar ,  Jun Wang

发明人： Sanjiv Kumar ,  Jun Wang

IPC分类号： G06F15/18 ,  G06N99/00

CPC分类号： G06N99/005 ,  H04L9/3236

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating hash functions. In one aspect, a method includes generating hash functions by sequentially determining a weight vector for each hash function to maximize an accuracy measure derived from current constraint weights and updating the current constraint weights for use in calculating a weight vector of a next hash function in the sequence. In another aspect, the determined weight vector maximizes an accuracy measure and a variance measure. In still another aspect, a method includes generating an adjusted covariance matrix and generating a sequence of hash functions from the adjusted covariance matrix. In still another aspect, a method includes sequentially generating a sequence of hash functions, where the weight vectors for any previously generated hash functions are used to identify constraints used to generate the weight vector for each next hash function in the sequence.

公开(公告)号：US08924339B1

公开(公告)日：2014-12-30

申请号：US13183939

申请日：2011-07-15

申请人： Sanjiv Kumar ,  Jun Wang

发明人： Sanjiv Kumar ,  Jun Wang

IPC分类号： G06F17/00 ,  G06N7/04

CPC分类号： G06N99/005 ,  H04L9/3236

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating hash functions. In one aspect, a method includes generating hash functions by sequentially determining a weight vector for each hash function to maximize an accuracy measure derived from current constraint weights and updating the current constraint weights for use in calculating a weight vector of a next hash function in the sequence. In another aspect, the determined weight vector maximizes an accuracy measure and a variance measure. In still another aspect, a method includes generating an adjusted covariance matrix and generating a sequence of hash functions from the adjusted covariance matrix. In still another aspect, a method includes sequentially generating a sequence of hash functions, where the weight vectors for any previously generated hash functions are used to identify constraints used to generate the weight vector for each next hash function in the sequence.

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，用于生成散列函数。 一方面，一种方法包括：通过依次确定每个散列函数的加权向量来产生哈希函数，以使从当前约束权重导出的精度度量最大化并更新当前约束权重，以用于计算下一个哈希函数的权重向量 序列。 在另一方面，确定的权重向量使精度测量和方差测量最大化。 在另一方面，一种方法包括生成经调整的协方差矩阵，并从调整的协方差矩阵生成散列函数序列。 在另一方面，一种方法包括依次生成散列函数序列，其中用于任何先前生成的散列函数的加权向量用于识别用于生成序列中每个下一个散列函数的加权向量的约束。

公开(公告)号：US08510236B1

公开(公告)日：2013-08-13

申请号：US13103992

申请日：2011-05-09

申请人： Sanjiv Kumar ,  Jun Wang

发明人： Sanjiv Kumar ,  Jun Wang

IPC分类号： G06F15/18

CPC分类号： G06N99/005 ,  H04L9/3236

摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating hash functions. In one aspect, a method includes generating hash functions by sequentially determining a weight vector for each hash function to maximize an accuracy measure derived from current constraint weights and updating the current constraint weights for use in calculating a weight vector of a next hash function in the sequence. In another aspect, the determined weight vector maximizes an accuracy measure and a variance measure. In still another aspect, a method includes generating an adjusted covariance matrix and generating a sequence of hash functions from the adjusted covariance matrix. In still another aspect, a method includes sequentially generating a sequence of hash functions, where the weight vectors for any previously generated hash functions are used to identify constraints used to generate the weight vector for each next hash function in the sequence.

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，用于生成散列函数。 一方面，一种方法包括：通过依次确定每个散列函数的加权向量来产生哈希函数，以使从当前约束权重导出的精度度量最大化并更新当前约束权重，以用于计算下一个哈希函数的权重向量 序列。 在另一方面，确定的权重向量使精度测量和方差测量最大化。 在另一方面，一种方法包括生成经调整的协方差矩阵，并从调整的协方差矩阵生成散列函数序列。 在另一方面，一种方法包括依次生成散列函数序列，其中用于任何先前生成的散列函数的加权向量用于识别用于生成序列中每个下一个散列函数的加权向量的约束。

公开(公告)号：US20130198601A1

公开(公告)日：2013-08-01

申请号：US13799307

申请日：2013-03-13

申请人： Ameesh Makadia ,  Sanjiv Kumar

发明人： Ameesh Makadia ,  Sanjiv Kumar

IPC分类号： G06F17/24

CPC分类号： G06F17/241 ,  G06F17/30265 ,  G06K9/00664 ,  G06K9/46

摘要： Methods, systems, and apparatus, including computer program products, for generating data for annotating images automatically. In one aspect, a method includes receiving an input image, identifying one or more nearest neighbor images of the input image from among a collection of images, in which each of the one or more nearest neighbor images is associated with a respective one or more image labels, assigning a plurality of image labels to the input image, in which the plurality of image labels are selected from the image labels associated with the one or more nearest neighbor images, and storing in a data repository the input image having the assigned plurality of image labels. In another aspect, a method includes assigning a single image label to the input image, in which the single image label is selected from labels associated with multiple ranked nearest neighbor images.

公开(公告)号：US08477998B1

公开(公告)日：2013-07-02

申请号：US13309999

申请日：2011-12-02

申请人： Minyoung Kim ,  Sanjiv Kumar ,  Henry A. Rowley

发明人： Minyoung Kim ,  Sanjiv Kumar ,  Henry A. Rowley

IPC分类号： G06K9/00

CPC分类号： G06K9/00261 ,  G06K9/6214 ,  G06K9/6264 ,  G06K9/6277

摘要： Embodiments of the present invention relate to object tracking in video. In an embodiment, a computer-implemented method tracks an object in a frame of a video. An adaptive term value is determined based on an adaptive model and at least a portion of the frame. A pose constraint value is determined based on a pose model and at least a portion the frame. An alignment confidence score is determined based on an alignment model and at least a portion the frame. Based on the adaptive term value, the pose constraint value, and the alignment confidence score, an energy value is determined. Based on the energy value, a resultant tracking state is determined. The resultant tracking state defines a likely position of the object in the frame given the object's likely position in a set of previous frames in the video.

摘要翻译： 本发明的实施例涉及视频中的对象跟踪。 在一个实施例中，计算机实现的方法跟踪视频帧中的对象。 基于自适应模型和帧的至少一部分来确定自适应项值。 基于姿态模型和帧的至少一部分来确定姿势约束值。 基于对准模型和框架的至少一部分来确定对准置信度得分。 基于自适应项值，姿态约束值和对准置信度得分，确定能量值。 基于能量值，确定合成的跟踪状态。 所得到的跟踪状态定义了给定对象在视频中的一组先前帧中的可能位置的帧中的对象的可能位置。

公开(公告)号：US08301498B1

公开(公告)日：2012-10-30

申请号：US13488126

申请日：2012-06-04

申请人： Corinna Cortes ,  Sanjiv Kumar ,  Ameesh Makadia ,  Gideon Mann ,  Jay Yagnik ,  Ming Zhao

发明人： Corinna Cortes ,  Sanjiv Kumar ,  Ameesh Makadia ,  Gideon Mann ,  Jay Yagnik ,  Ming Zhao

IPC分类号： G06Q30/00 ,  G06N5/02

CPC分类号： H04N21/2407 ,  G06F17/30784 ,  G06F17/30817 ,  G06F17/3082 ,  G06F17/30828 ,  G06K9/00711 ,  H04N21/23418 ,  H04N21/25883 ,  H04N21/4668 ,  H04N21/4826

摘要： A video demographics analysis system selects a training set of videos to use to correlate viewer demographics and video content data. The video demographics analysis system extracts demographic data from viewer profiles related to videos in the training set and creates a set of demographic distributions, and also extracts video data from videos in the training set. The video demographics analysis system correlates the viewer demographics with the video data of videos viewed by that viewer. Using the prediction model produced by the machine learning process, a new video about which there is no a priori knowledge can be associated with a predicted demographic distribution specifying probabilities of the video appealing to different types of people within a given demographic category, such as people of different ages within an age demographic category.

摘要翻译： 视频人口统计分析系统选择用于将观众人口特征和视频内容数据相关联的一组视频。 视频人口统计分析系统从与训练集中的视频相关的观众简档中提取人口统计学数据，并创建一组人口分布，并从训练集中的视频中提取视频数据。 视频人口统计分析系统将观众人口统计学与观众观看的视频的视频数据相关联。 使用机器学习过程产生的预测模型，可以将预测的人口分布与预测的人口分布相关联，所述预测人口统计分布规定了给定人口统计学类别中的不同类型的人的视频的概率，例如人 在不同年龄的人口统计学类别。

公开(公告)号：US20090304272A1

公开(公告)日：2009-12-10

申请号：US12425910

申请日：2009-04-17

申请人： Ameesh Makadia ,  Sanjiv Kumar

发明人： Ameesh Makadia ,  Sanjiv Kumar

IPC分类号： G06K9/68 ,  G06K9/00

CPC分类号： G06F17/241 ,  G06F17/30265 ,  G06K9/00664 ,  G06K9/46

摘要： Methods, systems, and apparatus, including computer program products, for generating data for annotating images automatically. In one aspect, a method includes receiving an input image, identifying one or more nearest neighbor images of the input image from among a collection of images, in which each of the one or more nearest neighbor images is associated with a respective one or more image labels, assigning a plurality of image labels to the input image, in which the plurality of image labels are selected from the image labels associated with the one or more nearest neighbor images, and storing in a data repository the input image having the assigned plurality of image labels. In another aspect, a method includes assigning a single image label to the input image, in which the single image label is selected from labels associated with multiple ranked nearest neighbor images.

摘要翻译： 方法，系统和装置，包括计算机程序产品，用于自动生成用于注释图像的数据。 一方面，一种方法包括接收输入图像，从图像集合中识别输入图像的一个或多个最近邻图像，其中所述一个或多个最近邻图像中的每一个与相应的一个或多个图像相关联 标签，将多个图像标签分配给输入图像，其中从与一个或多个最近邻图像相关联的图像标签中选择多个图像标签，并且在数据存储库中存储具有分配的多个图像标签的输入图像 图像标签。 在另一方面，一种方法包括向输入图像分配单个图像标签，其中从与多个排序的最邻近图像相关联的标签中选择单个图像标签。

公开(公告)号：US20150066649A1

公开(公告)日：2015-03-05

申请号：US12768101

申请日：2010-04-27

申请人： Sanjiv Kumar ,  Jason Weston

发明人： Sanjiv Kumar ,  Jason Weston

IPC分类号： G01C21/00 ,  G06Q30/00

CPC分类号： G06Q50/14 ,  G01C21/3476 ,  G06Q30/02

摘要： Systems and methods provide touristic routes to users. For example, a user at a client device may request a touristic route between an initial and a final destination. A server uses the initial and final destinations to determine a shortest route. The server then defines an envelope around the route in order to identify points of interest. The identified points of interest are ranked and filtered, in order to select the most relevant points of interest. Once the points of interest are selected, the server determines a final route between the initial destination, the points of interest, and the final route. This information is then transmitted to the client device and displayed to the user. The server may also identify and transmit content associated with the final route and/or the points of interest, including, but not limited to, photos, videos, hyperlinks, and advertisements.

摘要翻译： 系统和方法为用户提供旅游路线。 例如，客户端设备上的用户可以请求在初始和最终目的地之间的旅游路由。 服务器使用初始和最终目的地来确定最短路由。 然后，服务器在路线周围定义一个信封，以便识别感兴趣的点。 对所识别的兴趣点进行排序和筛选，以便选择最相关的兴趣点。 一旦选择兴趣点，服务器确定初始目的地，兴趣点和最终路线之间的最终路线。 然后将该信息发送到客户端设备并显示给用户。 服务器还可以识别和发送与最终路线和/或兴趣点相关联的内容，包括但不限于照片，视频，超链接和广告。

公开(公告)号：US08781231B1

公开(公告)日：2014-07-15

申请号：US12547303

申请日：2009-08-25

申请人： Sanjiv Kumar ,  Henry A. Rowley ,  Ameesh Makadia

发明人： Sanjiv Kumar ,  Henry A. Rowley ,  Ameesh Makadia

IPC分类号： G06K9/54

CPC分类号： G06F17/30274 ,  G06F17/30247 ,  G06K9/6215 ,  G06K9/6224 ,  G06K2209/27

摘要： Methods, systems, and apparatus, including computer program products, for ranking search results for queries. The method includes calculating a visual similarity score for one or more pairs of images in a plurality of images based on visual features of images in each of the one or more pairs; building a graph of images by linking each of one or more images in the plurality of images to one or more nearest neighbor images based on the visual similarity scores; associating a respective score with each of one or more images in the graph based on data indicative of user behavior relative to the image as a search result for a query; and determining a new score for each of one or more images in the graph based on the respective score of the image, and the respective scores of one or more nearest neighbors to the image.

摘要翻译： 方法，系统和装置，包括计算机程序产品，用于对查询的搜索结果进行排名。 该方法包括基于一个或多个对中的每一个中的图像的视觉特征来计算多个图像中的一对或多对图像的视觉相似性分数; 通过基于所述视觉相似性得分将所述多个图像中的一个或多个图像的每一个链接到一个或多个最近邻图像来构建图像的图; 基于表示用户相对于图像的行为的数据作为查询的搜索结果，将各个分数与图中的一个或多个图像中的每一个相关联; 以及基于所述图像的相应分数以及所述图像的一个或多个最近邻居的各个分数来确定所述图中的一个或多个图像中的每一个的新分数。