公开(公告)号：US09508023B1

公开(公告)日：2016-11-29

申请号：US14257683

申请日：2014-04-21

Applicant: Google Inc.

Inventor： Matthew Sharifi ,  Sergey Ioffe ,  Jay Yagnik ,  Gheorghe Postelnicu ,  Dominik Roblek ,  George Tzanetakis

IPC: G06F17/30 ,  G06K9/62 ,  G06K9/00

CPC classification number: G06K9/6267 ,  G06F17/3002 ,  G06F17/30244 ,  G06K9/00013

Abstract: This disclosure relates to transformation invariant media matching. A fingerprinting component can generate a transformation invariant identifier for media content by adaptively encoding the relative ordering of interest points in media content. The interest points can be grouped into subsets, and stretch invariant descriptors can be generated for the subsets based on ratios of coordinates of interest points included in the subsets. The stretch invariant descriptors can be aggregated into a transformation invariant identifier. An identification component compares the identifier against a set of identifiers for known media content, and the media content can be matched or identified as a function of the comparison.

Abstract translation: 本公开涉及变换不变媒体匹配。 指纹分量可以通过对媒体内容中的兴趣点的相对排序进行自适应编码来生成媒体内容的变换不变标识符。 可以将兴趣点分组为子集，并且可以基于子集中包括的兴趣点坐标的比例为子集生成拉伸不变描述符。 拉伸不变描述符可以聚合成变换不变标识符。 识别部件将标识符与已知媒体内容的一组标识符进行比较，并且媒体内容可以作为比较的函数进行匹配或标识。

公开(公告)号：US20160014440A1

公开(公告)日：2016-01-14

申请号：US13632591

申请日：2012-10-01

Applicant: Google Inc.

Inventor： CORINNA CORTES ,  SANJIV KUMAR ,  Ameesh Makadia ,  Gideon Mann ,  Jay Yagnik ,  Ming Zhao

IPC: H04N21/24

CPC classification number: H04N21/2407 ,  G06F16/735 ,  G06F16/78 ,  G06F16/783 ,  G06F16/7867 ,  G06K9/00711 ,  H04N21/23418 ,  H04N21/25883 ,  H04N21/4668 ,  H04N21/4826

Abstract: 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.

Abstract translation: 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：US09135674B1

公开(公告)日：2015-09-15

申请号：US14092515

申请日：2013-11-27

Applicant: Google Inc.

Inventor： Jay Yagnik ,  Henry Rowley ,  Sergey Ioffe

IPC: G06F17/00 ,  G06T1/00

CPC classification number: G06T1/0021 ,  G06F17/30784 ,  G06F17/30787 ,  G06K9/00744 ,  G06K9/00758

Abstract: A method and system generates and compares fingerprints for videos in a video library. The video fingerprints provide a compact representation of the temporal locations of discontinuities in the video that can be used to quickly and efficiently identify video content. Discontinuities can be, for example, shot boundaries in the video frame sequence or silent points in the audio stream. Because the fingerprints are based on structural discontinuity characteristics rather than exact bit sequences, visual content of videos can be effectively compared even when there are small differences between the videos in compression factors, source resolutions, start and stop times, frame rates, and so on. Comparison of video fingerprints can be used, for example, to search for and remove copyright protected videos from a video library. Furthermore, duplicate videos can be detected and discarded in order to preserve storage space.

Abstract translation: 方法和系统生成并比较视频库中视频的指纹。 视频指纹提供了可以用于快速和有效地识别视频内容的视频中的不连续性的时间位置的紧凑表示。 不连续可以是例如视频帧序列中的镜头边界或音频流中的无声点。 因为指纹是基于结构不连续特征而不是精确的比特序列，所以即使在压缩因素，源分辨率，开始和停止时间，帧率等之间的视频之间存在小的差异，也可以有效地比较视频的视觉内容 。 可以使用比较视频指纹，例如，从视频库搜索和删除受版权保护的视频。 此外，为了保存存储空间，可以检测和丢弃重复的视频。

公开(公告)号：US20150081604A1

公开(公告)日：2015-03-19

申请号：US14552001

申请日：2014-11-24

Applicant: Google Inc.

Inventor： Juan Carlos Niebles Duque ,  Hrishikesh Aradhye ,  Luciano Sbaiz ,  Jay Yagnik ,  Reto Strobl

IPC: G06N5/04 ,  G06N99/00

CPC classification number: G06N99/005 ,  G06F17/30781 ,  G06K9/00744 ,  H04L65/4084 ,  H04N21/23418 ,  H04N21/252 ,  H04N21/25883 ,  H04N21/25891

Abstract: A demographics analysis trains classifier models for predicting demographic attribute values of videos and users not already having known demographics. In one embodiment, the demographics analysis system trains classifier models for predicting demographics of videos using video features such as demographics of video uploaders, textual metadata, and/or audiovisual content of videos. In one embodiment, the demographics analysis system trains classifier models for predicting demographics of users (e.g., anonymous users) using user features based on prior video viewing periods of users. For example, viewing-period based user features can include individual viewing period statistics such as total videos viewed. Further, the viewing-period based features can include distributions of values over the viewing period, such as distributions in demographic attribute values of video uploaders, and/or distributions of viewings over hours of the day, days of the week, and the like.

Abstract translation: 人口统计学分析训练分类器模型，用于预测未知人口统计信息的视频和用户的人口特性值。 在一个实施例中，人口统计分析系统训练分类器模型，以使用诸如视频上传者的人口统计学，文本元数据和/或视频的视听内容的视频特征来预测视频的人口统计。 在一个实施例中，人口统计分析系统训练分类器模型，以基于用户的先前视频观看时段使用用户特征来预测用户（例如，匿名用户）的人口统计。 例如，基于观看期的用户特征可以包括个体观看期间统计，例如观看的总视频。 此外，基于观看期间的特征可以包括在观看期间的值的分布，诸如视频上传者的人口统计属性值中的分布，和/或一天中的几天，星期几等的观看次数分布。

公开(公告)号：US08788503B1

公开(公告)日：2014-07-22

申请号：US14036037

申请日：2013-09-25

Applicant: Google Inc.

Inventor： Jay Yagnik

IPC: G06F17/30 ,  G06F7/00

CPC classification number: G06K9/6219 ,  G06F17/30247 ,  G06K9/00684

Abstract: Systems, computer program products, and methods can identify a training set of content, and generate one or more clusters from the training set of content, where each of the one or more clusters represent similar features of the training set of content. The one or more clusters can be used to generate a classifier. New content is identified and the classifier is used to associate at least one label with the new content.

Abstract translation: 系统，计算机程序产品和方法可以识别内容的训练集，并且从内容的训练集合生成一个或多个聚类，其中一个或多个聚类中的每一个表示训练集合的相似特征。 一个或多个聚类可用于生成分类器。 识别新内容，并且使用分类器将至少一个标签与新内容相关联。

公开(公告)号：US09971940B1

公开(公告)日：2018-05-15

申请号：US15231445

申请日：2016-08-08

Applicant: Google Inc.

Inventor： Luciano Sbaiz ,  Jay Yagnik ,  King Hong Thomas Leung ,  Hanna Pasula ,  Thomas Chadwick Walters ,  Thomas Bugnon ,  Matthias Rochus Konrad

IPC: G06K9/62 ,  G06K9/00 ,  G06F21/32 ,  G06N3/04

CPC classification number: G06K9/00758 ,  G06F21/10 ,  G06F2221/074 ,  G06K9/00718 ,  G06K9/00765 ,  G06K9/6215 ,  G06K9/6255 ,  G06K9/6269 ,  G06N3/04

Abstract: Provided content is determined to contain an asset represented by reference content by comparing digital fingerprints of the provided content and the reference content. The fingerprints of the reference content and the provided content are generated using a convolutional neural network (CNN). The CNN is trained using a plurality of frame triplets including an anchor frame representing the reference content, a positive frame which is a transformation of the anchor frame, and a negative frame representing content that is not the reference content. The provided content is determined to contain the asset represented by the reference content based on a similarity measure between the generated fingerprints. If the provided content is determined to contain the asset represented by the reference content, a policy associated with the asset is enforced on the provided content.

公开(公告)号：US09569847B1

公开(公告)日：2017-02-14

申请号：US14622623

申请日：2015-02-13

Applicant: Google Inc.

Inventor： Dennis Strelow ,  Jay Yagnik

IPC: G06K9/00 ,  G06T7/00 ,  G06F17/16

CPC classification number: G06F17/16 ,  G06F17/11 ,  G06T7/246 ,  G06T7/70 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/30244

Abstract: One of the described methods includes receiving a plurality of images from a camera, the plurality of images comprising a sequence; identifying one or more two-dimensional features in each of a plurality of images in the received sequence of images; associating a three-dimensional point with each of the identified one or more two-dimensional features; tracking each of the one or more two-dimensional features through successive images in the plurality of images; and iteratively minimizing a two-dimensional image error between the tracked each of the one or more two-dimensional features and an image reprojection with respect to the three-dimensional point corresponding to the one or more two-dimensional features and a three-dimensional position of the camera corresponding to one or more of the plurality of images.

Abstract translation: 所描述的方法之一包括从相机接收多个图像，所述多个图像包括序列; 识别所接收的图像序列中的多个图像中的每一个中的一个或多个二维特征; 将三维点与所识别的一个或多个二维特征中的每一个相关联; 通过所述多个图像中的连续图像跟踪所述一个或多个二维特征中的每一个; 并且迭代地最小化所述一个或多个二维特征中的所跟踪的每个之间的二维图像误差和相对于对应于所述一个或多个二维特征的三维点的图像重投影，以及三维位置 所述相机对应于所述多个图像中的一个或多个。

公开(公告)号：US20160180200A1

公开(公告)日：2016-06-23

申请号：US14933256

申请日：2015-11-05

Applicant: Google Inc.

Inventor： Sudheendra Vijayanarasimhan ,  Jay Yagnik

IPC: G06K9/62 ,  G06K9/66 ,  G06N3/04

CPC classification number: G06K9/6267 ,  G06K9/66 ,  G06N3/04 ,  G06N3/082

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classification using a neural network. One of the methods for processing an input through each of multiple layers of a neural network to generate an output, wherein each of the multiple layers of the neural network includes a respective multiple nodes includes for a particular layer of the multiple layers: receiving, by a classification system, an activation vector as input for the particular layer, selecting one or more nodes in the particular layer using the activation vector and a hash table that maps numeric values to nodes in the particular layer, and processing the activation vector using the selected nodes to generate an output for the particular layer.

Abstract translation: 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，用于使用神经网络进行分类。 用于处理通过神经网络的多个层中的每一层的输入以产生输出的方法之一，其中所述神经网络的所述多个层中的每一个包括针对所述多个层的特定层的相应多个节点包括：通过 分类系统，作为特定层的输入的激活向量，使用激活向量选择特定层中的一个或多个节点，以及将数值映射到特定层中的节点的哈希表，以及使用所选择的处理激活向量 节点来生成特定层的输出。

公开(公告)号：US10061999B1

公开(公告)日：2018-08-28

申请号：US15339616

申请日：2016-10-31

Applicant: Google Inc.

Inventor： Vivek Kwatra ,  Jay Yagnik ,  Alexander Toshkov Toshev

IPC: G06K9/62 ,  G06K9/32 ,  G06T7/00

CPC classification number: G06K9/3241 ,  G06K9/00771 ,  G06K9/468 ,  G06K9/6255 ,  G06T7/11 ,  G06T7/174 ,  G06T2207/20081

Abstract: An example method is disclosed that includes identifying a training set of images, wherein each image in the training set has an identified bounding box that comprises an object class and an object location for an object in the image. The method also includes segmenting each image of the training set, wherein segments comprise sets of pixels that share visual characteristics, and wherein each segment is associated with an object class. The method further includes clustering the segments that are associated with the same object class, and generating a data structure based on the clustering, wherein entries in the data structure comprise visual characteristics for prototypical segments of objects having the object class and further comprise one or more potential bounding boxes for the objects, wherein the data structure is usable to predict bounding boxes of additional images that include an object having the object class.

公开(公告)号：US09870383B1

公开(公告)日：2018-01-16

申请号：US14684046

申请日：2015-04-10

Applicant: Google Inc.

Inventor： Jay Yagnik

IPC: G06F17/00 ,  G06F17/30

CPC classification number: G06F17/3033 ,  G06F17/30309 ,  G06K9/4676 ,  H04L9/3236

Abstract: The disclosed embodiments describe a method, an apparatus, an application specific integrated circuit, and a server that provides a fast and efficient look up for data analysis. The apparatus and server may be configured to obtain data segments from a plurality of input devices. The data segments may be individual unique subsets of the entire data set obtained by a plurality input devices. A hash function may be applied to an aggregated set of the data segments. A result of the hash function may be stored in a data structure. A codebook may be generated from the hash function results.