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

US08819024B1 Learning category classifiers for a video corpus 有权
标题翻译：学习视频语料库的类别分类器
公开(公告)号：US08819024B1
公开(公告)日：2014-08-26
申请号：US12950955
申请日：2010-11-19
申请人： George Toderici , Hrishikesh Aradhye , Alexandru Marius Pasca , Luciano Sbaiz , Jay Yagnik
发明人： George Toderici , Hrishikesh Aradhye , Alexandru Marius Pasca , Luciano Sbaiz , Jay Yagnik
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/30731 , G06K9/00718
摘要： A classifier training system learns classifiers for categories by combining data from a category-instance repository comprising relationships between categories and more specific instances of those categories with a set of video classifiers for different concepts. The category-instance repository is derived from the domain of textual documents, such as web pages, and the concept classifiers are derived from the domain of video. Taken together, the category-instance repository and the concept classifiers provide sufficient data for obtaining accurate classifiers for categories that encompass other lower-level concepts, where the categories and their classifiers may not be obtainable solely from the video domain.
摘要翻译：分类器训练系统通过将包括类别之间的关系的类别实例存储库的数据与这些类别的更具体的实例组合用于不同概念的一组视频分类器来学习类别的分类器。类别实例存储库是从文本文档的领域（如Web页面）导出的，概念分类器是从视频域派生的。总而言之，类别实例存储库和概念分类器提供足够的数据，以便为包含其他较低级别概念的类别获取准确的分类器，其中类别及其分类可能无法仅从视频域获得。

2. 发明授权

US08990134B1 Learning to geolocate videos 有权
标题翻译：学习定位视频
公开(公告)号：US08990134B1
公开(公告)日：2015-03-24
申请号：US12881078
申请日：2010-09-13
申请人： Jasper Snoek , Luciano Sbaiz , Hrishikesh Aradhye , George Toderici
发明人： Jasper Snoek , Luciano Sbaiz , Hrishikesh Aradhye , George Toderici
IPC分类号： G06K9/62
CPC分类号： G06K9/00697 , G06F17/30784
摘要： A classifier training system trains classifiers for inferring the geographic locations of videos. A number of classifiers are provided, where each classifier corresponds to a particular location and is trained from a training set of videos that have been labeled as representing the location. In one embodiment, the training set is further restricted to those videos in which a landmark matching the location label is detected. The classifier training system extracts, from each of these videos, features that characterize the video, such as audiovisual features, text features, address features, landmark features, and category features. Based on these features, the classifier training system trains a location classifier for the corresponding location.Each of the location classifiers can be applied to videos without associated location labels to predict whether, or how strongly, the video represents the corresponding location. The prediction can be used for a variety of purposes, such as automatic labeling of videos with locations, presentation of location-specific advertisements in association with videos, and display of video data on relevant portions of an electronic map.
摘要翻译：分类器训练系统训练用于推断视频地理位置的分类器。提供了多个分类器，其中每个分类器对应于特定位置，并且从被标记为表示位置的训练集合的训练中训练。在一个实施例中，训练集进一步限于那些其中检测到与位置标签匹配的地标的视频。分类器训练系统从每个这些视频中提取表征视频的功能，例如视听功能，文本功能，地址功能，地标功能和类别功能。基于这些特征，分类器训练系统为相应的位置训练位置分类器。每个位置分类器都可以应用于没有相关位置标签的视频，以预测视频是表示相应位置还是多强。该预测可以用于各种目的，诸如具有位置的视频的自动标记，与视频相关联的位置特定广告的呈现以及在电子地图的相关部分上的视频数据的显示。

3. 发明授权

US08396286B1 Learning concepts for video annotation 有权
标题翻译：学习视频注释的概念
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。

4. 发明授权

US09179192B1 Associating video content with geographic maps 有权
标题翻译：将视频内容与地理地图相关联
公开(公告)号：US09179192B1
公开(公告)日：2015-11-03
申请号：US13561981
申请日：2012-07-30
申请人： Huazhong Ning , Hrishikesh Aradhye
发明人： Huazhong Ning , Hrishikesh Aradhye
IPC分类号： H04H60/33 , H04N21/472 , H04N21/4725
CPC分类号： G06F17/3082 , G01C21/28 , G06F3/0482 , G06F3/04842 , G06F17/30241 , G06F17/30554 , G06F17/30572 , G06F17/3087 , G06K9/00476 , G06K9/00718 , G06T11/206 , H04N21/25841 , H04N21/4524 , H04N21/472 , H04N21/4725
摘要： A system and method for associating videos with geographic locations is disclosed. The system comprises a communication module, a location module, a tagging module and a database association module. The communication module receives a video uploaded by a content provider and a set of video data describing the video. The location module determines that the video describes a geographic location included in a geographic map based at least in part on the video data. The tagging module determines one or more travelling tags for the video based at least in part on the video data. The database association module associates the video and the one or more travelling tags with the geographic location so that the video with the one or more travelling tags is included in the geographic map.
摘要翻译：公开了一种用于将视频与地理位置相关联的系统和方法。该系统包括通信模块，位置模块，标签模块和数据库关联模块。通信模块接收由内容提供商上传的视频和描述该视频的一组视频数据。位置模块至少部分地基于视频数据来确定视频描述包括在地理地图中的地理位置。至少部分地基于视频数据，标签模块确定用于视频的一个或多个旅行标签。数据库关联模块将视频和一个或多个旅行标签与地理位置相关联，使得具有一个或多个旅行标签的视频被包括在地理地图中。

5. 发明授权

US08510238B1 Method to predict session duration on mobile devices using native machine learning 有权
标题翻译：使用本地机器学习预测移动设备上的会话持续时间的方法
公开(公告)号：US08510238B1
公开(公告)日：2013-08-13
申请号：US13585503
申请日：2012-08-14
申请人： Hrishikesh Aradhye , Ruei-sung Lin
发明人： Hrishikesh Aradhye , Ruei-sung Lin
IPC分类号： G06F15/18
CPC分类号： G06N99/005 , H04W4/50 , H04W16/22
摘要： Methods and apparatus for predicting time spans for mobile platform activation are presented. A machine-learning service executing on a mobile platform receives feature-related data. The feature-related data includes usage-related data about time spans that the mobile platform is activated and platform-related data received from the mobile platform. The usage-related data and the platform-related data can differ. The machine-learning service determines whether the machine-learning service is trained to perform machine-learning operations related to predicting a time span that the mobile platform will be activated. In response to determining that the machine-learning service is trained, the machine-learning service: receives a request for a predicted time span that the mobile platform will be activated, determines the predicted time span by the machine-learning service performing a machine-learning operation on the feature-related data, and sends the predicted time span.
摘要翻译：提出了用于预测移动平台激活时间跨度的方法和装置。在移动平台上执行的机器学习服务接收特征相关数据。功能相关数据包括关于移动平台被激活的时间跨度和从移动平台接收的与平台相关的数据的使用相关数据。使用相关数据和平台相关数据可能不同。机器学习服务确定机器学习服务是否被训练以执行与预测移动平台将被激活的时间跨度相关的机器学习操作。响应于确定机器学习服务被训练，机器学习服务：接收对移动平台将被激活的预测时间跨度的请求，通过执行机器学习服务的机器学习服务来确定预测的时间间隔，对功能相关数据进行学习操作，并发送预测时间段。

6. 发明授权

US08665238B1 Determining a dominant hand of a user of a computing device 有权
标题翻译：确定计算设备的用户的优势手
公开(公告)号：US08665238B1
公开(公告)日：2014-03-04
申请号：US13658632
申请日：2012-10-23
申请人： Richard Carl Gossweiler, III , Hrishikesh Aradhye
发明人： Richard Carl Gossweiler, III , Hrishikesh Aradhye
IPC分类号： G06F3/041
CPC分类号： G06F3/0481 , G06F3/0482 , G06F3/0488 , G06F3/04886
摘要： In one example, a method includes determining, by a computing device, a plurality of features. Each feature from the plurality of features may be usable to determine a dominant hand of a user of the computing device. The method also includes receiving, by the computing device, a plurality of input values, each input value from the plurality of input values corresponding to the respective plurality of features, and determining, using a probabilistic model and based at least in part on at least one input value from the plurality of input values corresponding to the respective feature from the plurality of features, a hand of the user as a dominant hand of the user. The method also includes generating, based at least in part on the determined dominant hand of the user, a graphical user interface for display at a presence-sensitive display operatively coupled to the computing device.
摘要翻译：在一个示例中，方法包括由计算设备确定多个特征。来自多个特征的每个特征可以用于确定计算设备的用户的优势手。所述方法还包括由所述计算设备接收多个输入值，来自所述多个输入值的对应于所述相应多个特征的每个输入值，以及使用概率模型并且至少部分至少基于至少来自与来自多个特征的各个特征相对应的多个输入值中的一个输入值，作为用户的优势手的用户的手。该方法还包括至少部分地基于所确定的用户的优势手，生成用于在可操作地耦合到计算设备的存在敏感显示器上显示的图形用户界面。

7. 发明授权

US08531519B1 Automatic multi-device localization and collaboration using cameras 有权
标题翻译：使用相机自动多设备本地化和协作
公开(公告)号：US08531519B1
公开(公告)日：2013-09-10
申请号：US13605194
申请日：2012-09-06
申请人： Yifan Peng , Wei Hua , Hrishikesh Aradhye , Rodrigo Carceroni
发明人： Yifan Peng , Wei Hua , Hrishikesh Aradhye , Rodrigo Carceroni
IPC分类号： H04N7/18 , G06K9/66
CPC分类号： H04N7/18
摘要： Implementations relate to a computer-implemented method and a device for determining a relative posed between devices. The method can include receiving data representing first keypoint features from a first image captured by a camera of a second mobile computing device; capturing, by a camera of a first mobile computing device, a second image, wherein the first image and the second image comprise a substantially common scene having an area of overlap; computing, by the first mobile computing device, data representing second keypoint features from the second image; determining, by the first mobile computing device, based at least in part on the data representing first keypoint features and the data representing second keypoint features, a relative pose of the first mobile computing device and the second mobile computing device; and communicating the relative pose to the second mobile computing device.
摘要翻译：实现涉及计算机实现的方法和用于确定设备之间的相对设置的设备。该方法可以包括从由第二移动计算设备的相机捕获的第一图像接收表示第一关键点特征的数据; 通过第一移动计算设备的相机捕获第二图像，其中所述第一图像和所述第二图像包括具有重叠区域的基本上共同的场景; 由所述第一移动计算设备计算表示来自所述第二图像的第二关键点特征的数据; 至少部分地基于表示第一关键点特征的数据和表示第二关键点特征的数据确定第一移动计算设备和第二移动计算设备的相对姿态; 以及将所述相对姿势传达给所述第二移动计算设备。

8. 发明申请

US20070242858A1 Method and apparatus for person identification 有权
标题翻译：人身识别的方法和装置
公开(公告)号：US20070242858A1
公开(公告)日：2007-10-18
申请号：US11253901
申请日：2005-10-19
申请人： Hrishikesh Aradhye , Martin Fischler , Robert Bolles , Gregory Myers
发明人： Hrishikesh Aradhye , Martin Fischler , Robert Bolles , Gregory Myers
IPC分类号： G06K9/00 , G06K9/46
CPC分类号： G07C9/00158 , A45D44/005 , G06K9/00362 , G06K9/4652
摘要： A method and apparatus are provided for person identification. In one embodiment, a method for identifying an individual includes obtaining at least one image of the individual, where the image depicts at least a portion of the individual's hair, comparing the visual characteristics of the individual's hair to the visual characteristics of imaged hair in one or more stored images, and identifying the individual based on the comparison.
摘要翻译：提供了一种用于人员识别的方法和装置。在一个实施例中，用于识别个体的方法包括获得个体的至少一个图像，其中图像描绘个人头发的至少一部分，将个体的头发的视觉特征与一个成像的头发的视觉特征进行比较或更多存储的图像，并且基于比较来识别个体。

9. 发明授权

US08913103B1 Method and apparatus for focus-of-attention control 有权
标题翻译：焦点控制的方法和装置
公开(公告)号：US08913103B1
公开(公告)日：2014-12-16
申请号：US13363948
申请日：2012-02-01
申请人： Emre Sargin , Rodrigo Carceroni , Huazhong Ning , Wei Hua , Marius Renn , Hrishikesh Aradhye
发明人： Emre Sargin , Rodrigo Carceroni , Huazhong Ning , Wei Hua , Marius Renn , Hrishikesh Aradhye
IPC分类号： H04N7/14
CPC分类号： G06K9/00221 , G06K9/00335 , G06K9/00711 , H04N7/14 , H04N21/42203 , H04N21/4394 , H04N21/44218
摘要： Disclosed are methods for automatically generating commands to transform a video sequence based on information regarding speaking participants derived from the audio and video signals. The audio stream is analyzed to detect individual speakers and the video is optionally analyzed to detect lip movement to determine a probability that a detected participant is speaking. Commands are then generated to transform the video stream consistent with the identified speaker.
摘要翻译：公开了一种用于基于从音频和视频信号导出的关于说话参与者的信息来自动生成用于变换视频序列的命令的方法。分析音频流以检测单个扬声器，并且可选地分析视频以检测唇部移动以确定检测到的参与者正在说话的概率。然后生成命令以转换与所识别的扬声器一致的视频流。

10. 发明授权

US08258390B1 System and method for dynamic, feature-based playlist generation 有权
标题翻译：用于动态基于特征的播放列表生成的系统和方法
公开(公告)号：US08258390B1
公开(公告)日：2012-09-04
申请号：US13251119
申请日：2011-09-30
申请人： Rich Gossweiler , Douglas Eck , Hrishikesh Aradhye , Tomas Izo
发明人： Rich Gossweiler , Douglas Eck , Hrishikesh Aradhye , Tomas Izo
IPC分类号： G10H1/00
CPC分类号： G06F17/30053 , G06F17/30749 , G06F17/30772 , G10H2240/081 , G10H2240/121 , G11B27/034 , G11B27/105
摘要： Methods and systems for generating playlists of media items with audio data are disclosed. Based on two received feature sets, media items corresponding to each feature set are identified. Transition characteristics are also received. Based on the identified media items and transition characteristics, a dynamic playlist is generated that transitions from media items having characteristics of the first feature set to media items having characteristics of the second feature set. Each time the playlist is generated, it may include a different set of media items.
摘要翻译：公开了用于产生具有音频数据的媒体项的播放列表的方法和系统。基于两个接收到的特征集，识别与每个特征集相对应的媒体项。也收到过渡特征。基于所识别的媒体项目和转换特征，生成从具有第一特征集合的媒体项目转换到具有第二特征集合的媒体项目的动态播放列表。每当生成播放列表时，它可以包括不同的媒体项目集合。

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