公开(公告)号：US08588525B1

公开(公告)日：2013-11-19

申请号：US13298957

申请日：2011-11-17

申请人： Jay Yagnik ,  Sergey Ioffe

发明人： Jay Yagnik ,  Sergey Ioffe

IPC分类号： G06K9/00

CPC分类号： H04N19/60 ,  G06K9/00744

摘要： 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 signal markers in media content. The signal markers can be adaptively encoded via reference point geometry, or ratio histograms. 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.

公开(公告)号：US08572099B2

公开(公告)日：2013-10-29

申请号：US13007209

申请日：2011-01-14

申请人： Shumeet Baluja ,  Yushi Jing ,  Dandapani Sivakumar ,  Jay Yagnik

发明人： Shumeet Baluja ,  Yushi Jing ,  Dandapani Sivakumar ,  Jay Yagnik

IPC分类号： G06F17/30 ,  G06Q30/00

CPC分类号： G06Q30/02 ,  G06Q30/0274 ,  G06Q30/0277

摘要： The subject matter of this specification can be embodied in, among other things, a method that includes generating content-based keywords based on content generated by users of a social network. The method includes labeling nodes comprising user nodes, which are representations of the users, with advertising labels comprising content-based keywords that coincide with advertiser-selected keywords that are based on one or more terms specified by an advertiser. The method also includes outputting, for each node, weights for the advertising labels based on weights of advertising labels associated with neighboring nodes, which are related to the node by a relationship.

摘要翻译： 本说明书的主题可以包括基于社交网络的用户生成的内容生成基于内容的关键词的方法。 该方法包括标示包括用户节点的节点，其是用户的表示，广告标签包括与基于广告商指定的一个或多个术语的广告商选择的关键字相符合的基于内容的关键字。 该方法还包括针对每个节点，根据通过关系与节点相关联的与相邻节点相关联的广告标签的权重，输出广告标签的权重。

公开(公告)号：US20130114902A1

公开(公告)日：2013-05-09

申请号：US13601802

申请日：2012-08-31

申请人： Rahul Sukthankar ,  Jay Yagnik

发明人： Rahul Sukthankar ,  Jay Yagnik

IPC分类号： G06K9/46

CPC分类号： H04N9/8205 ,  G06K9/00718 ,  G06K9/00744 ,  H04N21/23418

摘要： A volume identification system identifies a set of unlabeled spatio-temporal volumes within each of a set of videos, each volume representing a distinct object or action. The volume identification system further determines, for each of the videos, a set of volume-level features characterizing the volume as a whole. In one embodiment, the features are based on a codebook and describe the temporal and spatial relationships of different codebook entries of the volume. The volume identification system uses the volume-level features, in conjunction with existing labels assigned to the videos as a whole, to label with high confidence some subset of the identified volumes, e.g., by employing consistency learning or training and application of weak volume classifiers.The labeled volumes may be used for a number of applications, such as training strong volume classifiers, improving video search (including locating individual volumes), and creating composite videos based on identified volumes.

摘要翻译： 体积识别系统识别一组视频中的每一个中的一组未标记的时空体积，每个体积表示不同的对象或动作。 音量识别系统进一步为每个视频确定表征整个音量的一组音量级特征。 在一个实施例中，特征基于码本并且描述卷的不同码本条目的时间和空间关系。 音量识别系统使用音量级特征，结合分配给整个视频的现有标签，以高度置信的方式标识所识别的体积的一些子集，例如通过采用一致性学习或训练和应用弱音量分类器 。 标记的卷可以用于许多应用，例如训练强大的分类器，改进视频搜索（包括定位各个卷），以及基于识别的卷创建复合视频。

公开(公告)号：US08417751B1

公开(公告)日：2013-04-09

申请号：US13289416

申请日：2011-11-04

申请人： Jay Yagnik

发明人： Jay Yagnik

IPC分类号： G06F17/10 ,  G06F17/15 ,  G06K9/64

CPC分类号： G06F17/15 ,  G06K9/6202

摘要： Convolutions are frequently used in signal processing. A method for performing an ordinal convolution is disclosed. In an embodiment of the disclosed subject matter, an ordinal mask may be obtained. The ordinal mask may describe a property of a signal. A representation of a signal may be received. A processor may convert the representation of the signal to an ordinal representation of the signal. The ordinal mask may be applied to the ordinal representation of the signal. Based upon the application of the ordinal mask to the ordinal representation of the signal, it may be determined that the property is present in the signal. The ordinal convolution method described herein may be applied to any type of signal processing method that relies on a transform or convolution.

摘要翻译： 卷积经常用于信号处理。 公开了一种执行顺序卷积的方法。 在所公开的主题的实施例中，可以获得顺序掩模。 序数掩码可以描述信号的属性。 可以接收信号的表示。 处理器可以将信号的表示转换为信号的序数表示。 序数掩码可以应用于信号的顺序表示。 基于将序数掩码应用于信号的顺序表示，可以确定信号中存在该属性。 这里描述的顺序卷积方法可以应用于依赖于变换或卷积的任何类型的信号处理方法。

公开(公告)号：US08396286B1

公开(公告)日：2013-03-12

申请号：US12822727

申请日：2010-06-24

申请人： Hrishikesh Aradhye ,  George Toderici ,  Jay Yagnik

发明人： Hrishikesh Aradhye ,  George Toderici ,  Jay Yagnik

IPC分类号： G06K9/62 ,  G06K9/66 ,  G06K9/00

CPC分类号： G06K9/00718 ,  G06K9/6262

摘要： A concept learning module trains video classifiers associated with a stored set of concepts derived from textual metadata of a plurality of videos, the training based on features extracted from training videos. Each of the video classifiers can then be applied to a given video to obtain a score indicating whether or not the video is representative of the concept associated with the classifier. The learning process does not require any concepts to be known a priori, nor does it require a training set of videos having training labels manually applied by human experts. Rather, in one embodiment the learning is based solely upon the content of the videos themselves and on whatever metadata was provided along with the video, e.g., on possibly sparse and/or inaccurate textual metadata specified by a user of a video hosting service who submitted the video.

摘要翻译： 概念学习模块训练与从多个视频的文本元数据导出的存储的一组概念相关联的视频分类器，该训练基于从训练视频中提取的特征。 然后可以将每个视频分类器应用于给定的视频以获得指示视频是否代表与分类器相关联的概念的分数。 学习过程不需要先验知道任何概念，也不需要由人类专家手动应用培训标签的培训视频。 相反，在一个实施例中，学习仅基于视频本身的内容以及与视频一起提供的任何元数据，例如，由提交的视频托管服务的用户指定的可能稀疏和/或不准确的文本元数据 视频。

公开(公告)号：US08385662B1

公开(公告)日：2013-02-26

申请号：US12432989

申请日：2009-04-30

申请人： Sangho Yoon ,  Jay Yagnik ,  Mei Han ,  Vivek Kwatra

发明人： Sangho Yoon ,  Jay Yagnik ,  Mei Han ,  Vivek Kwatra

IPC分类号： G06K9/62

CPC分类号： G06K9/6247 ,  G06K9/6223

摘要： Clustering algorithms such as k-means clustering algorithm are used in applications that process entities with spatial and/or temporal characteristics, for example, media objects representing audio, video, or graphical data. Feature vectors representing characteristics of the entities are partitioned using clustering methods that produce results sensitive to an initial set of cluster seeds. The set of initial cluster seeds is generated using principal component analysis of either the complete feature vector set or a subset thereof. The feature vector set is divided into a desired number of initial clusters and a seed determined from each initial cluster.

摘要翻译： 诸如k均值聚类算法的聚类算法被用于处理具有空间和/或时间特征的实体的应用中，例如表示音频，视频或图形数据的媒体对象。 使用产生对初始集群种子集合敏感的结果的聚类方法对代表实体特征的特征向量进行分区。 使用完整特征向量集或其子集的主成分分析来生成初始簇种子集合。 特征向量集合被分为期望数量的初始簇和从每个初始簇确定的种子。

公开(公告)号：US08239418B1

公开(公告)日：2012-08-07

申请号：US13397576

申请日：2012-02-15

申请人： Shumeet Baluja ,  Yushi Jing ,  Dandapani Sivakumar ,  Jay Yagnik

发明人： Shumeet Baluja ,  Yushi Jing ,  Dandapani Sivakumar ,  Jay Yagnik

IPC分类号： G06F17/30

CPC分类号： G06F17/30035 ,  G06F17/30828 ,  G06Q30/02 ,  Y10S707/99942 ,  Y10S707/99945

摘要： The subject matter of this specification can be embodied in, among other things, a method that includes inferring labels for videos, users, advertisements, groups of users, and other entities included in a social network system. The inferred labels can be used to generate recommendations such as videos or advertisements in which a user may be interested. Inferred labels can be generated based on social or other relationships derived from, for example, profiles or activities of social network users. Inferred labels can be advantageous when explicit information about these entities is not available. For example, a particular user may not have clicked on any online advertisements, so the user is not explicitly linked to any advertisements.

摘要翻译： 本说明书的主题可以包括推断用于视频，用户，广告，用户组以及包括在社交网络系统中的其他实体的标签的方法。 推断的标签可用于生成用户可能感兴趣的建议，如视频或广告。 可以基于从例如社交网络用户的简档或活动导出的社会或其他关系来生成推断标签。 当关于这些实体的显式信息不可用时，推断的标签可能是有利的。 例如，特定用户可能没有点击任何在线广告，因此用户没有明确地链接到任何广告。

公开(公告)号：US08140451B1

公开(公告)日：2012-03-20

申请号：US13183375

申请日：2011-07-14

申请人： Ullas Gargi ,  Jay Yagnik

发明人： Ullas Gargi ,  Jay Yagnik

IPC分类号： G06F11/00

CPC分类号： G06K9/00536 ,  G06K9/00516

摘要： Disclosed herein is a method, a system and a computer program product for generating a statistical classification model used by a computer system to determine a class associated with an unlabeled time series event. Initially, a set of labeled time series events is received. A set of time series features is identified for a selected set of the labeled time series events. A plurality of scale space decompositions is generated based on the set of time series features. A plurality of multi-scale features is generated based on the plurality of scale space decompositions. A first subset of the plurality of multi-scale features that correspond at least in part to a subset of space or time points within a time series event that contain feature data that distinguish the time series event as belonging to a class of time series events that corresponds to the class label are identified. A statistical classification model for classifying an unlabeled time series event based on the class corresponding with the class label is generated based at least in part on the at the first subset of the plurality of multi-scale features.

摘要翻译： 本文公开了一种用于生成由计算机系统用于确定与未标记的时间序列事件相关联的类别的统计分类模型的方法，系统和计算机程序产品。 最初，接收一组标记的时间序列事件。 针对所选择的一组标记的时间序列事件识别一组时间序列特征。 基于该组时间序列特征生成多个比例空间分解。 基于多个刻度空间分解产生多个多尺度特征。 所述多个多尺度特征的第一子集至少部分对应于时间序列事件内的空间或时间点的子集，所述时间序列事件包含将所述时间序列事件区分为属于一类时间序列事件的特征数据，所述时间序列事件 对应于类标签被识别。 至少部分地基于多个多尺度特征的第一子集来生成用于基于与类标签相对应的类来分类未标记时间序列事件的统计分类模型。

公开(公告)号：US08094872B1

公开(公告)日：2012-01-10

申请号：US11746339

申请日：2007-05-09

申请人： Jay Yagnik ,  Henry A. Rowley ,  Sergey Ioffe

发明人： Jay Yagnik ,  Henry A. Rowley ,  Sergey Ioffe

IPC分类号： G06K9/00 ,  G06K9/46 ,  H04L9/32 ,  H04N7/167

CPC分类号： G06K9/00711 ,  H04N21/23418

摘要： A method and system generates and compares fingerprints for videos in a video library. The video fingerprints provide a compact representation of the spatial and sequential characteristics of the video that can be used to quickly and efficiently identify video content. Because the fingerprints are based on spatial and sequential 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. Further, duplicate videos can be detected and discarded in order to preserve storage space.

摘要翻译： 方法和系统生成并比较视频库中视频的指纹。 视频指纹提供了可用于快速有效地识别视频内容的视频的空间和顺序特征的紧凑表示。 因为指纹是基于空间和顺序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 上。 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：US08001062B1

公开(公告)日：2011-08-16

申请号：US11952436

申请日：2007-12-07

申请人： Ullas Gargi ,  Jay Yagnik

发明人： Ullas Gargi ,  Jay Yagnik

IPC分类号： G06F11/00

CPC分类号： G06K9/00536 ,  G06K9/00516

摘要： Disclosed herein is a method, a system and a computer program product for generating a statistical classification model used by a computer system to determine a class associated with an unlabeled time series event. Initially, a set of labeled time series events is received. A set of time series features is identified for a selected set of the labeled time series events. A plurality of scale space decompositions is generated based on the set of time series features. A plurality of multi-scale features is generated based on the plurality of scale space decompositions. A first subset of the plurality of multi-scale features that correspond at least in part to a subset of space or time points within a time series event that contain feature data that distinguish the time series event as belonging to a class of time series events that corresponds to the class label are identified. A statistical classification model for classifying an unlabeled time series event based on the class corresponding with the class label is generated based at least in part on the at the first subset of the plurality of multi-scale features.

摘要翻译： 本文公开了一种用于生成由计算机系统用于确定与未标记的时间序列事件相关联的类别的统计分类模型的方法，系统和计算机程序产品。 最初，接收一组标记的时间序列事件。 针对所选择的一组标记的时间序列事件识别一组时间序列特征。 基于该组时间序列特征生成多个比例空间分解。 基于多个刻度空间分解产生多个多尺度特征。 所述多个多尺度特征的第一子集至少部分对应于时间序列事件内的空间或时间点的子集，所述时间序列事件包含将所述时间序列事件区分为属于一类时间序列事件的特征数据，所述时间序列事件 对应于类标签被识别。 至少部分地基于多个多尺度特征的第一子集来生成用于基于与类标签相对应的类来分类未标记时间序列事件的统计分类模型。