专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

51. 发明授权

US08340449B1 Three-dimensional wavelet based video fingerprinting 有权
公开(公告)号：US08340449B1
公开(公告)日：2012-12-25
申请号：US13250494
申请日：2011-09-30
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
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.

52. 发明授权

US08301498B1 Video content analysis for automatic demographics recognition of users and videos 有权
标题翻译：用于用户和视频的自动人口统计识别的视频内容分析
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。

53. 发明授权

US08165414B1 Vector transformation for indexing, similarity search and classification 有权
标题翻译：矢量变换索引，相似搜索和分类
公开(公告)号：US08165414B1
公开(公告)日：2012-04-24
申请号：US13288706
申请日：2011-11-03
申请人： Jay Yagnik
发明人： Jay Yagnik
IPC分类号： G06K9/40 , G06E1/00
CPC分类号： G06F17/3002 , G06K2009/4695
摘要： A feature vector is encoded into a sparse binary vector. The feature vector is retrieved, for example from storage or a feature vector generator. The feature vector represents a media object or other data object. One or more permutations are generated, the dimensionality of the generated permutations equivalent to the dimensionality of the feature vector. The permutations may be generated randomly or formulaically. The feature vector is permuted with the one or more permutations, creating one or more permuted feature vectors. The permuted feature vectors are truncated according to a selected window size. The indexes representing the maximum values of the permuted feature vectors are identified and encoded using one-hot encoding, producing one or more sparse binary vectors. The sparse binary vectors may be concatenated into a single sparse binary vector and stored. The sparse binary vector may be used in the similarity search, indexing or categorization of media objects.
摘要翻译：特征向量被编码成稀疏二进制向量。例如从存储或特征向量生成器检索特征向量。特征向量表示媒体对象或其他数据对象。产生一个或多个排列，所产生的排列的维数等于特征向量的维数。排列可以随机或公式地产生。特征向量与一个或多个排列置换，创建一个或多个置换的特征向量。根据所选择的窗口尺寸来截断重排的特征向量。代表置换特征向量的最大值的索引使用单热编码进行识别和编码，产生一个或多个稀疏二进制向量。稀疏二进制向量可以被级联成单个稀疏二进制向量并被存储。稀疏二进制向量可以用于媒体对象的相似搜索，索引或分类。

54. 发明授权

US08131786B1 Training scoring models optimized for highly-ranked results 有权
标题翻译：培训评分模型针对高排名结果进行了优化
公开(公告)号：US08131786B1
公开(公告)日：2012-03-06
申请号：US12624001
申请日：2009-11-23
申请人： Samy Bengio , Gal Chechik , Sergey Ioffe , Jay Yagnik
发明人： Samy Bengio , Gal Chechik , Sergey Ioffe , Jay Yagnik
IPC分类号： G06F17/00
CPC分类号： G06K9/66 , G06F17/30244 , G06F17/3053 , G06K9/6267 , Y10S707/913 , Y10S707/915
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training scoring models. One method includes storing data identifying a plurality of positive and a plurality of negative training images for a query. The method further includes selecting a first image from either the positive group of images or the negative group of images, and applying a scoring model to the first image. The method further includes selecting a plurality of candidate images from the other group of images, applying the scoring model to each of the candidate images, and then selecting a second image from the candidate images according to scores for the images. The method further includes determining that the scores for the first image and the second image fail to satisfy a criterion, updating the scoring model, and storing the updated scoring model.
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，用于训练评分模型。一种方法包括存储识别用于查询的多个正训练图像和多个负训练图像的数据。该方法还包括从图像的正组或负图像组中选择第一图像，以及将评分模型应用于第一图像。该方法还包括从另一组图像中选择多个候选图像，将评分模型应用于每个候选图像，然后根据图像的分数从候选图像中选择第二图像。该方法还包括确定第一图像和第二图像的分数不能满足标准，更新评分模型，并存储更新的评分模型。

55. 发明授权

US07827123B1 Graph based sampling 有权
标题翻译：基于图形的抽样
公开(公告)号：US07827123B1
公开(公告)日：2010-11-02
申请号：US11840139
申请日：2007-08-16
申请人： Jay Yagnik
发明人： Jay Yagnik
IPC分类号： G06F15/18
CPC分类号： G06N99/005
摘要： An iterative method of sampling real world event data to generate a subset of data that is used for training a classifier. Graph Based Sampling uses an iterative process of evaluating and adding randomly selected event data sets to a training data set. In Graph Based Sampling, at each iteration, a two event data sets are randomly selected from a stored plurality of event data sets. A proximity function is used to generate a correlation or similarity value between each of these randomly selected real world event data sets, and the current training data set. One of the randomly selected event data sets is then added to the training data set based on the proximity value. This process of selection and addition is repeated until the subset of training set is a pre-determined size.
摘要翻译：对现实世界事件数据进行采样以生成用于训练分类器的数据子集的迭代方法。基于图形的采样使用迭代过程来评估和添加随机选择的事件数据集到训练数据集。在基于图形的抽样中，在每次迭代中，从存储的多个事件数据集中随机选择两个事件数据集。接近函数用于在这些随机选择的真实世界事件数据集和当前训练数据集之间产生相关性或相似性值。然后将随机选择的事件数据集之一基于接近度值加到训练数据集中。重复该选择和添加过程，直到训练集的子集为预定大小。

56. 发明申请

US20090052784A1 Detection And Classification Of Matches Between Time-Based Media 有权
标题翻译：基于时间的媒体匹配检测与分类
公开(公告)号：US20090052784A1
公开(公告)日：2009-02-26
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
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。

57. 发明授权

US09524487B1 System and methods for detecting temporal music trends from online services 有权
标题翻译：用于从在线服务中检测时间音乐趋势的系统和方法
公开(公告)号：US09524487B1
公开(公告)日：2016-12-20
申请号：US13466817
申请日：2012-05-08
申请人： Jay Yagnik , Douglas Eck
发明人： Jay Yagnik , Douglas Eck
IPC分类号： G06F15/16 , G06Q10/10 , G06F17/30 , G06Q30/00
CPC分类号： G06Q10/10 , G06F17/30 , G06Q30/00
摘要： A system and methods for automatically detecting temporal music trends by observing music consumption by users of online services, for example, social networks, and user sharing habits. In some embodiments, the system and methods gather music consumption patterns (e.g., downloading, listening, sharing or the like) of users, including music identifiers for a track, album, or playlist in a user's music library and time stamps that indicate consumption times corresponding to the music identifiers. A temporal trends detection engine determines music of interest to users by analyzing music consumption patterns of users, user interests and tastes in music, and social affinity between users. A recommendations engine automatically generates and transmits recommendations of music determined by the temporal trends detection engine to be of interest to users.
摘要翻译：用于通过观察在线服务的用户（例如，社交网络）和用户共享习惯的音乐消费来自动检测时间音乐趋势的系统和方法。在一些实施例中，系统和方法收集用户的音乐消费模式（例如，下载，收听，共享等），包括用户音乐库中的音轨，专辑或播放列表的音乐标识符，以及指示消费时间的时间戳对应于音乐标识符。时间趋势检测引擎通过分析用户的音乐消费模式，音乐中的用户兴趣和品味以及用户之间的社交关系来确定用户感兴趣的音乐。推荐引擎自动生成并发送由时间趋势检测引擎确定的用户兴趣的音乐推荐。

58. 发明授权

US09483701B1 System and method for using segmentation to identify object location in images 有权
标题翻译：使用分割来识别图像中的对象位置的系统和方法
公开(公告)号：US09483701B1
公开(公告)日：2016-11-01
申请号：US13299281
申请日：2011-11-17
申请人： Vivek Kwatra , Jay Yagnik , Alexander T. Toshev
发明人： Vivek Kwatra , Jay Yagnik , Alexander T. Toshev
IPC分类号： G06K9/62 , G06K9/00 , G06K9/32
CPC分类号： G06K9/3241 , G06K9/00771 , G06K9/468 , G06K9/6255 , G06T7/0081 , G06T7/0097 , G06T2207/20081
摘要： A computing device segments an image into a plurality of segments, wherein each segment of the plurality of segments has a segment location and a set of pixels that share visual characteristics. The computing device determines an initial set of bounding boxes for the image based on the plurality of segments. The computing device determines a reduced set of bounding boxes based on combining bounding boxes of the initial set of bounding boxes, the reduced set of bounding boxes corresponding to one or more objects in the image, each of the one or more objects having an object class and an object location.
摘要翻译：计算设备将图像分割成多个段，其中多个段中的每个段具有共享视觉特征的段位置和一组像素。计算设备基于多个段确定图像的初始边界框集合。计算设备基于组合边界框的边界框来确定缩小的边界框集合，所述边界框对应于所述图像中的一个或多个对象，所述一个或多个对象中的每一个具有对象类和对象位置。

59. 发明授权

US09158842B1 Sound representation via winner-take-all coding of auditory spectra 有权
标题翻译：通过听觉光谱的获胜者全部编码的声音表示
公开(公告)号：US09158842B1
公开(公告)日：2015-10-13
申请号：US13616938
申请日：2012-09-14
申请人： Jay Yagnik , Richard Francis Lyon , Thomas Chadwick Walters , Douglas Eck
发明人： Jay Yagnik , Richard Francis Lyon , Thomas Chadwick Walters , Douglas Eck
IPC分类号： G06F17/30
CPC分类号： G06F17/30743 , G06F17/00 , G06F17/3074
摘要： Sound representations and winner-take-all codes of auditory spectra are used in the identification of audio content. A transformation component converts a set of sound frames from audio content into a set of spectral slices. A spectral encoder component encodes the spectral slices of auditory spectra into winner-take-all codes with a winner-take-all hash function. An identification component identifies which spectral dimension of a subset of spectral dimensions within a spectral slice has highest spectral value according to the winner-take-all codes. Reference audio content is determined to be similar or matching to the audio content based on the winner-take-all codes.
摘要翻译：听觉谱中的声音表示和获胜者代码都用于音频内容的识别。变换分量将一组声音帧从音频内容转换成一组光谱片段。频谱编码器组件将听觉光谱的频谱切片编成具有获胜者全部散列函数的获胜者所有代码。识别部件根据获胜者全部代码识别光谱切片内的光谱维度的子集的哪个光谱尺寸具有最高光谱值。参考音频内容被确定为基于获胜者所有代码与音频内容相似或匹配。

60. 发明授权

US08977374B1 Geometric and acoustic joint learning 有权
标题翻译：几何和声学联合学习
公开(公告)号：US08977374B1
公开(公告)日：2015-03-10
申请号：US13610866
申请日：2012-09-12
申请人： Douglas Eck , Jay Yagnik
发明人： Douglas Eck , Jay Yagnik
IPC分类号： G06F17/00 , G06F17/30 , G06F7/00 , G06G7/12 , H04H60/65 , H04H60/58 , G11B27/30 , H04H60/37 , H04H60/47 , H04H60/48
CPC分类号： H04H60/65 , G06F17/30778 , G10L25/63 , G11B27/105 , G11B27/28 , G11B27/3009 , H04H60/37 , H04H60/47 , H04H60/48 , H04H60/58
摘要： Described herein are methods and system for analyzing music audio. An example method includes obtaining a music audio track, calculating acoustic features of the music audio track, calculating geometric features of the music audio track in view of the acoustic features, and determining a mood of the music audio track in view of the geometric features.
摘要翻译：这里描述了用于分析音乐音频的方法和系统。示例性方法包括：获得音乐音轨，计算音乐音轨的声学特征，根据声学特征计算音乐音轨的几何特征，以及根据几何特征确定音乐音轨的情绪。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式