专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09454600B2 Refining image relevance models 有权
标题翻译：精炼图像相关模型
公开(公告)号：US09454600B2
公开(公告)日：2016-09-27
申请号：US13363979
申请日：2012-02-01
申请人： Thomas J. Duerig , Jason E. Weston , Charles J. Rosenberg , Kunlong Gu , Samy Bengio
发明人： Thomas J. Duerig , Jason E. Weston , Charles J. Rosenberg , Kunlong Gu , Samy Bengio
IPC分类号： G06K9/62 , G06K9/52 , G06F17/30 , G06K9/66
CPC分类号： G06F17/30675 , G06F17/3028 , G06K9/52 , G06K9/6202 , G06K9/6256 , G06K9/6262 , G06K9/6296 , G06K9/66
摘要： Methods, systems and apparatus for refining image relevance models. In general, one aspect includes receiving a trained image relevance model that generates relevance measures of content feature values of images to a query, identifying a first threshold number of common content feature values for the set of training images, the common content feature values being identified as a set of content feature values that are each shared by at least a portion of the training images, identifying a subset of the set of training images having a quantity of the common content feature values greater than a second threshold number of content features values, and generating a re-trained image relevance model based on content feature values of the set of training images, wherein content feature values of the subset of training images are weighted higher than content feature values of the training images not in the subset.
摘要翻译：图像相关模型的方法，系统和装置。通常，一个方面包括接收经过训练的图像相关性模型，该模型生成图像的内容特征值的相关性度量到查询，识别该组训练图像的公共内容特征值的第一阈值数量，所识别的共同内容特征值作为由训练图像的至少一部分共享的一组内容特征值，识别具有大于第二阈值数量的内容特征值的公共内容特征值的量的训练图像集合的子集，以及基于训练图像集合的内容特征值生成重新训练的图像相关性模型，其中训练图像的子集的内容特征值被加权高于不在该子集中的训练图像的内容特征值。

2. 发明授权

US08589457B1 Training scoring models optimized for highly-ranked results 有权
公开(公告)号：US08589457B1
公开(公告)日：2013-11-19
申请号：US13616108
申请日：2012-09-14
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.

3. 发明授权

US08463719B2 Audio classification for information retrieval using sparse features 有权
标题翻译：使用稀疏特征进行信息检索的音频分类
公开(公告)号：US08463719B2
公开(公告)日：2013-06-11
申请号：US12722437
申请日：2010-03-11
申请人： Richard F. Lyon , Martin Rehn , Thomas Walters , Samy Bengio , Gal Chechik
发明人： Richard F. Lyon , Martin Rehn , Thomas Walters , Samy Bengio , Gal Chechik
IPC分类号： G06F15/18
CPC分类号： G10L25/48 , G06F17/30743
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, are provided for using audio features to classify audio for information retrieval. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of generating a collection of auditory images, each auditory image being generated from respective audio files according to an auditory model; extracting sparse features from each auditory image in the collection to generate a sparse feature vector representing the corresponding audio file; and ranking the audio files in response to a query including one or more words using the sparse feature vectors and a matching function relating sparse feature vectors to words in the query.
摘要翻译：提供方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于使用音频特征来分类用于信息检索的音频。通常，本说明书中描述的主题的一个方面可以包括生成听觉图像的集合的动作的方法，每个听觉图像根据听觉模型从各个音频文件生成; 从集合中的每个听觉图像中提取稀疏特征以生成表示相应音频文件的稀疏特征向量; 以及响应于包括使用所述稀疏特征向量的一个或多个单词的查询和将稀疏特征向量与所述查询中的单词相关联的匹配函数进行排序。

4. 发明申请

US20120082371A1 LABEL EMBEDDING TREES FOR MULTI-CLASS TASKS 审中-公开
标题翻译：用于多类任务的标签嵌入条
公开(公告)号：US20120082371A1
公开(公告)日：2012-04-05
申请号：US12896318
申请日：2010-10-01
申请人： Samy Bengio , Jason E. Weston
发明人： Samy Bengio , Jason E. Weston
IPC分类号： G06K9/62
CPC分类号： G06K9/6282
摘要： Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for label embedding trees for large multi-class tasks. In one aspect, a method includes mapping each image in a plurality of images and each label in a plurality of labels into a multi-dimensional label embedding space. A tree of label predictors is trained with the plurality of mapped images such that an error function is minimized in which the error function counts an error for each mapped image if any of the label predictors at any depth of the tree incorrectly predicts that the mapped image belongs to the label predictor's respective label set.
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，用于为大型多类任务标签嵌入树。一方面，一种方法包括将多个图像中的每个图像和多个标签中的每个标签映射成多维标签嵌入空间。使用多个映射图像训练标签预测器的树，使得误差函数被最小化，其中如果在树的任何深度处的任何标签预测器错误地预测了映射图像，则误差函数计算每个映射图像的误差属于标签预测器的相应标签集。

5. 发明申请

US20100257129A1 AUDIO CLASSIFICATION FOR INFORMATION RETRIEVAL USING SPARSE FEATURES 有权
标题翻译：使用稀疏特征的信息检索的音频分类
公开(公告)号：US20100257129A1
公开(公告)日：2010-10-07
申请号：US12722437
申请日：2010-03-11
申请人： Robert F. Lyon , Martin Rehn , Thomas Walters , Samy Bengio , Gal Chechik
发明人： Robert F. Lyon , Martin Rehn , Thomas Walters , Samy Bengio , Gal Chechik
IPC分类号： G06F17/30 , G06F15/18
CPC分类号： G10L25/48 , G06F17/30743
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, are provided for using audio features to classify audio for information retrieval. In general, one aspect of the subject matter described in this specification can be embodied in methods that include the actions of generating a collection of auditory images, each auditory image being generated from respective audio files according to an auditory model; extracting sparse features from each auditory image in the collection to generate a sparse feature vector representing the corresponding audio file; and ranking the audio files in response to a query including one or more words using the sparse feature vectors and a matching function relating sparse feature vectors to words in the query.
摘要翻译：提供方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于使用音频特征来分类用于信息检索的音频。通常，本说明书中描述的主题的一个方面可以包括生成听觉图像的集合的动作的方法，每个听觉图像根据听觉模型从各个音频文件生成; 从集合中的每个听觉图像中提取稀疏特征以生成表示相应音频文件的稀疏特征向量; 以及响应于包括使用所述稀疏特征向量的一个或多个单词的查询和将稀疏特征向量与查询中的单词相关联的匹配函数进行排序。

6. 发明授权

US10055493B2 Generating a playlist 有权
公开(公告)号：US10055493B2
公开(公告)日：2018-08-21
申请号：US13103445
申请日：2011-05-09
申请人： Geremy A. Heitz, III , Adam Berenzweig , Jason E. Weston , Ron J. Weiss , Sally A. Goldman , Thomas Walters , Samy Bengio , Douglas Eck , Jay M. Ponte , Ryan M. Rifkin
发明人： Geremy A. Heitz, III , Adam Berenzweig , Jason E. Weston , Ron J. Weiss , Sally A. Goldman , Thomas Walters , Samy Bengio , Douglas Eck , Jay M. Ponte , Ryan M. Rifkin
IPC分类号： G06F17/30
CPC分类号： G06F16/639 , G06F16/683
摘要： Generating a playlist may include designating a seed track in an audio library; identifying audio tracks in the audio library having constructs that are within a range of a corresponding construct of the seed track, where the constructs for the audio tracks are derived from frequency representations of the audio tracks, and the corresponding construct for the seed track is derived from a frequency representation of the seed track; and generating the playlist using at least some of the audio tracks that were identified.

7. 发明授权

US08515212B1 Image relevance model 有权
公开(公告)号：US08515212B1
公开(公告)日：2013-08-20
申请号：US12505287
申请日：2009-07-17
申请人： Samy Bengio , Erik Murphy-Chutorian , Yangli Hector Yee , Charles Rosenberg
发明人： Samy Bengio , Erik Murphy-Chutorian , Yangli Hector Yee , Charles Rosenberg
IPC分类号： G06F17/30268 , G06K9/66 , G06K9/6256 , G06F17/30265 , G06F17/30244 , G06F17/30247
CPC分类号： G06F17/30256 , G06F17/30271 , G06K9/6223 , G06K9/6262
摘要： Methods, systems, and apparatus, including computer program products, for identifying images relevant to a query are disclosed. An image search subsystem selects images to reference in image search results that are responsive to a query based on an image relevance model that is trained for the query. An independent image relevance model is trained for each unique query that is identified by the image search subsystem. The image relevance models can be applied to images to order image search results obtained for the query. Each relevance model is trained based on content feature values of images that are identified as being relevant to the query (e.g., frequently selected from the image search results) and images that are identified as being relevant to another unique query. The trained model is applied to the content feature values of all known images to generate an image relevance score that can be used to order search results for the query.

8. 发明授权

US6018517A Process for the renewal--during communication--of the traffic parameters of an ATM network 失效
标题翻译：在通信期间更新ATM网络的流量参数的过程
公开(公告)号：US6018517A
公开(公告)日：2000-01-25
申请号：US803273
申请日：1997-02-20
申请人： Samy Bengio , Fabrice Clerot , Annie Gravey , Daniel Collobert
发明人： Samy Bengio , Fabrice Clerot , Annie Gravey , Daniel Collobert
IPC分类号： H04Q3/00 , H04L12/54 , H04L12/70 , G01R31/08 , G06F11/00 , G08C15/00 , H04J3/16
CPC分类号： H04L12/5602 , H04L2012/5632 , H04L2012/5634
摘要： A process for renegotiating, during a communication, the parameters of a traffic contract on an ATM network.The present invention relates to a renegotiation process, during a communication on an ATM network, of the parameters of the traffic contract that relates to this communication. It is characterized in that it consists:a. in predicting, for a predetermined period of time between two successive renegotiations, the maximal length that would be reached by a virtual file fed by the traffic of said communication, for at least a given thruput rate of said file.b. in deducing from said maximal length one or more new parameters for the traffic contract, andc. in renegotiating with the network on the basis of said (new) traffic parameter or parameters for said period of time.
摘要翻译：在通信期间重新谈判ATM网络上的交通合同的参数的过程。本发明涉及一种在ATM网络上的通信过程中与该通信相关的交通合同的参数的重新协商过程。它的特点是它包括：a。在预测两次连续重新协商之间的预定时间段内，为所述文件的至少一个给定的猝发速率预测由所述通信的业务所馈送的虚拟文件将达到的最大长度。 b。从所述最大长度推导出交通契约的一个或多个新参数，以及c。在所述（新的）流量参数或所述时间段的参数的基础上与网络重新谈判。

9. 发明授权

US09110922B2 Joint embedding for item association 有权
标题翻译：联合嵌入项目关联
公开(公告)号：US09110922B2
公开(公告)日：2015-08-18
申请号：US13019221
申请日：2011-02-01
申请人： Samy Bengio , Jason Weston
发明人： Samy Bengio , Jason Weston
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30244 , G06F17/30879
摘要： Methods and systems to associate semantically-related items of a plurality of item types using a joint embedding space are disclosed. The disclosed methods and systems are scalable to large, web-scale training data sets. According to an embodiment, a method for associating semantically-related items of a plurality of item types includes embedding training items of a plurality of item types in a joint embedding space configured in a memory coupled to at least one processor, learning one or more mappings into the joint embedding space for each of the item types to create a trained joint embedding space and one or more learned mappings, and associating one or more embedded training items with a first item based upon a distance in the trained joint embedding space from the first item to each said associated embedded training items. Exemplary item types that may be embedded in the joint embedding space include images, annotations, audio and video.
摘要翻译：公开了使用联合嵌入空间来关联多个项目类型的语义相关项目的方法和系统。所公开的方法和系统可扩展到大型的web规模的训练数据集。根据实施例，一种用于关联多个项目类型的语义相关项目的方法包括：将多个项目类型的训练项目嵌入到配置在耦合到至少一个处理器的存储器中的联合嵌入空间中，学习一个或多个映射进入用于每个项目类型的联合嵌入空间以创建经训练的联合嵌入空间和一个或多个学习的映射，以及基于训练的关节嵌入空间中的距离与第一项目相关联的一个或多个嵌入式训练项目与第一项目项目对每个说相关的嵌入式培训项目。可以嵌入在联合嵌入空间中的示例性项目类型包括图像，注释，音频和视频。

10. 发明授权

US08855430B1 Refining image annotations 有权
标题翻译：精简图片注释
公开(公告)号：US08855430B1
公开(公告)日：2014-10-07
申请号：US13527783
申请日：2012-06-20
申请人： Neil G. Alldrin , Charles J. Rosenberg , Bin Shen , Samy Bengio , Zhen Hao Zhou
发明人： Neil G. Alldrin , Charles J. Rosenberg , Bin Shen , Samy Bengio , Zhen Hao Zhou
IPC分类号： G06K9/62
CPC分类号： G06F17/30268 , G06K9/00664
摘要： Methods, systems and apparatus for refining image annotations. In one aspect, a method includes receiving, for each image in a set of images, a corresponding set of labels determined to be indicative of subject matter of the image. For each label, one or more confidence values are determined. Each confidence value is a measure of confidence that the label accurately describes the subject matter of a threshold number of respective images to which it corresponds. Labels for which each of the one or more confidence values meets a respective confidence threshold are identified as high confidence labels. For each image in the set of images, labels in its corresponding set of labels that are high confidence labels are identified. Images having a corresponding set of labels that include at least a respective threshold number of high confidence labels are identified as high confidence images.
摘要翻译：改进图像注释的方法，系统和设备。在一个方面，一种方法包括：对于图像集合中的每个图像，接收确定为指示图像主题的相应标签集合。对于每个标签，确定一个或多个置信度值。每个置信度值是对标签准确地描述其对应的各个图像的阈值数目的主题的置信度的度量。将一个或多个置信度值中的每一个满足相应置信度阈值的标签识别为高置信度标签。对于图像集合中的每个图像，识别其相应的标签组中的高置信度标签的标签。具有包括至少相应的阈值数量的高置信度标签的相应标签组的图像被识别为高置信度图像。

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