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

US07953693B2 Method and apparatus for ontology-based classification of media content 有权
标题翻译：用于基于本体的媒体内容分类的方法和装置
公开(公告)号：US07953693B2
公开(公告)日：2011-05-31
申请号：US12105192
申请日：2008-04-17
申请人： John R. Smith , Belle L. Tseng , Yi Wu
发明人： John R. Smith , Belle L. Tseng , Yi Wu
IPC分类号： G06F9/44 , G06N7/02 , G06N7/06
CPC分类号： G06K9/00711 , G06K9/6292 , Y10S707/99935 , Y10S707/99943
摘要： A method and apparatus for ontology-based classification of media content are provided. With the method and apparatus, initial confidence values of classifiers in a hierarchical classification structure are modified based on relationships between classifiers. A confidence value for a classifier is boosted by a boosting factor based on a correspondence between the confidence value and confidence values of ancestor classifiers in the hierarchical classification structure. A confidence value for a classifier is modified by a confusion factor based on a correspondence between the confidence value of the classifier and the confidence values of mutually exclusive classifiers in the hierarchical classification structure. In this way, a more accurate representation of the actual confidence that media content falls within the classification associated with the classifier is obtained. From this improved classification mechanism, indices for media content may be generated for use in accessing the media content at a later time.
摘要翻译：提供了一种用于基于本体的媒体内容分类的方法和装置。利用该方法和装置，基于分类器之间的关系来修改分层分类结构中分类器的初始置信度值。基于分级分类结构中的祖先分类器的置信度值和置信度值之间的对应关系，通过增强因子来提高分类器的置信度值。基于分类器的置信度值与层次分类结构中互斥分类器的置信度值之间的对应关系，通过混淆因子来修改分类器的置信度值。以这种方式，获得媒体内容落入与分类器相关联的分类内的实际置信度的更准确的表示。根据该改进的分类机制，可以生成用于媒体内容的索引以用于在稍后的时间访问媒体内容。

2. 发明申请

US20090327200A1 Method and Apparatus for Ontology-Based Classification of Media Content 有权
标题翻译：基于本体的媒体内容分类方法与装置
公开(公告)号：US20090327200A1
公开(公告)日：2009-12-31
申请号：US12105192
申请日：2008-04-17
申请人： John R. Smith , Belle L. Tseng , Yi Wu
发明人： John R. Smith , Belle L. Tseng , Yi Wu
IPC分类号： G06N5/02 , G06F17/30
CPC分类号： G06K9/00711 , G06K9/6292 , Y10S707/99935 , Y10S707/99943
摘要： A method and apparatus for ontology-based classification of media content are provided. With the method and apparatus, initial confidence values of classifiers in a hierarchical classification structure are modified based on relationships between classifiers. A confidence value for a classifier is boosted by a boosting factor based on a correspondence between the confidence value and confidence values of ancestor classifiers in the hierarchical classification structure. A confidence value for a classifier is modified by a confusion factor based on a correspondence between the confidence value of the classifier and the confidence values of mutually exclusive classifiers in the hierarchical classification structure. In this way, a more accurate representation of the actual confidence that media content falls within the classification associated with the classifier is obtained. From this improved classification mechanism, indices for media content may be generated for use in accessing the media content at a later time.
摘要翻译：提供了一种用于基于本体的媒体内容分类的方法和装置。利用该方法和装置，基于分类器之间的关系来修改分层分类结构中分类器的初始置信度值。基于分级分类结构中的祖先分类器的置信度值和置信度值之间的对应关系，通过增强因子来提高分类器的置信度值。基于分类器的置信度值与层次分类结构中互斥分类器的置信度值之间的对应关系，通过混淆因子来修改分类器的置信度值。以这种方式，获得媒体内容落入与分类器相关联的分类内的实际置信度的更准确的表示。根据该改进的分类机制，可以生成用于媒体内容的索引以用于在稍后的时间访问媒体内容。

3. 发明授权

US07873642B2 Method and apparatus for ontology-based classification of media content 有权
公开(公告)号：US07873642B2
公开(公告)日：2011-01-18
申请号：US11971252
申请日：2008-01-09
申请人： John R. Smith , Belle L. Tseng , Yi Wu
发明人： John R. Smith , Belle L. Tseng , Yi Wu
IPC分类号： G06F17/20 , G06F15/16
CPC分类号： G06K9/00711 , G06K9/6292 , Y10S707/99935 , Y10S707/99943
摘要： A method and apparatus for ontology-based classification of media content are provided. With the method and apparatus, initial confidence values of classifiers in a hierarchical classification structure are modified based on relationships between classifiers. A confidence value for a classifier is boosted by a boosting factor based on a correspondence between the confidence value and confidence values of ancestor classifiers in the hierarchical classification structure. A confidence value for a classifier is modified by a confusion factor based on a correspondence between the confidence value of the classifier and the confidence values of mutually exclusive classifiers in the hierarchical classification structure. In this way, a more accurate representation of the actual confidence that media content falls within the classification associated with the classifier is obtained. From this improved classification mechanism, indices for media content may be generated for use in accessing the media content at a later time.

4. 发明申请

US20080133466A1 METHOD AND APPARATUS FOR ONTOLOGY-BASED CLASSIFICATION OF MEDIA CONTENT 有权
标题翻译：用于基于媒体内容分类的方法和装置
公开(公告)号：US20080133466A1
公开(公告)日：2008-06-05
申请号：US11971252
申请日：2008-01-09
申请人： JOHN R. SMITH , Belle L. Tseng , Yi Wu
发明人： JOHN R. SMITH , Belle L. Tseng , Yi Wu
IPC分类号： G06F17/30
CPC分类号： G06K9/00711 , G06K9/6292 , Y10S707/99935 , Y10S707/99943
摘要： A method and apparatus for ontology-based classification of media content are provided. With the method and apparatus, initial confidence values of classifiers in a hierarchical classification structure are modified based on relationships between classifiers. A confidence value for a classifier is boosted by a boosting factor based on a correspondence between the confidence value and confidence values of ancestor classifiers in the hierarchical classification structure. A confidence value for a classifier is modified by a confusion factor based on a correspondence between the confidence value of the classifier and the confidence values of mutually exclusive classifiers in the hierarchical classification structure. In this way, a more accurate representation of the actual confidence that media content falls within the classification associated with the classifier is obtained. From this improved classification mechanism, indices for media content may be generated for use in accessing the media content at a later time.
摘要翻译：提供了一种用于基于本体的媒体内容分类的方法和装置。利用该方法和装置，基于分类器之间的关系来修改分层分类结构中分类器的初始置信度值。基于分级分类结构中的祖先分类器的置信度值和置信度值之间的对应关系，通过增强因子来提高分类器的置信度值。基于分类器的置信度值与层次分类结构中互斥分类器的置信度值之间的对应关系，通过混淆因子来修改分类器的置信度值。以这种方式，获得媒体内容落入与分类器相关联的分类内的实际置信度的更准确的表示。根据该改进的分类机制，可以生成用于媒体内容的索引以用于在稍后的时间访问媒体内容。

5. 发明授权

US07383260B2 Method and apparatus for ontology-based classification of media content 有权
标题翻译：用于基于本体的媒体内容分类的方法和装置
公开(公告)号：US07383260B2
公开(公告)日：2008-06-03
申请号：US10910118
申请日：2004-08-03
申请人： John R. Smith , Belle L. Tseng , Yi Wu
发明人： John R. Smith , Belle L. Tseng , Yi Wu
IPC分类号： G07F17/30 , G06F15/16
CPC分类号： G06K9/00711 , G06K9/6292 , Y10S707/99935 , Y10S707/99943
摘要： A method and apparatus for ontology-based classification of media content are provided. With the method and apparatus, initial confidence values of classifiers in a hierarchical classification structure are modified based on relationships between classifiers. A confidence value for a classifier is boosted by a boosting factor based on a correspondence between the confidence value and confidence values of ancestor classifiers in the hierarchical classification structure. A confidence value for a classifier is modified by a confusion factor based on a correspondence between the confidence value of the classifier and the confidence values of mutually exclusive classifiers in the hierarchical classification structure. In this way, a more accurate representation of the actual confidence that media content falls within the classification associated with the classifier is obtained. From this improved classification mechanism, indices for media content may be generated for use in accessing the media content at a later time.
摘要翻译：提供了一种用于基于本体的媒体内容分类的方法和装置。利用该方法和装置，基于分类器之间的关系来修改分层分类结构中分类器的初始置信度值。基于分级分类结构中的祖先分类器的置信度值和置信度值之间的对应关系，通过增强因子来提高分类器的置信度值。基于分类器的置信度值与层次分类结构中互斥分类器的置信度值之间的对应关系，通过混淆因子修改分类器的置信度值。以这种方式，获得媒体内容落入与分类器相关联的分类内的实际置信度的更准确的表示。根据该改进的分类机制，可以生成用于媒体内容的索引以用于在稍后的时间访问媒体内容。

6. 发明授权

US09716826B2 Guided image capture 有权
公开(公告)号：US09716826B2
公开(公告)日：2017-07-25
申请号：US13997990
申请日：2011-12-07
申请人： Yi Wu , Maha El Choubassi , Igor V. Kozintsev , Richard T. Beckwith , Kenneth T. Anderson , Maria Bezaitis
发明人： Yi Wu , Maha El Choubassi , Igor V. Kozintsev , Richard T. Beckwith , Kenneth T. Anderson , Maria Bezaitis
IPC分类号： H04N7/00 , H04N5/232 , H04N13/02
CPC分类号： H04N5/23222 , H04N5/23206 , H04N5/23238 , H04N13/211 , H04N13/296
摘要： Examples are disclosed for determining a suggested camera pose or suggested camera settings for a user to capture one or more images. In some examples, the suggested camera pose or suggested camera settings may be based on an indication of the user's interest and gathered information associated with the user's interests. The user may be guided to adjust an actual camera pose or actual camera settings to match the suggested camera pose or suggested camera settings.

7. 发明授权

US09418438B2 Networked capture and 3D display of localized, segmented images 有权
标题翻译：网络捕获和3D显示本地化，分段图像
公开(公告)号：US09418438B2
公开(公告)日：2016-08-16
申请号：US13977339
申请日：2011-09-12
申请人： Joshua Ratcliff , Yi Wu , Maha El Choubassi , Yoram Gat , Wei Sun , Kalpana Seshadrinathan , Igor V. Kozintsev
发明人： Joshua Ratcliff , Yi Wu , Maha El Choubassi , Yoram Gat , Wei Sun , Kalpana Seshadrinathan , Igor V. Kozintsev
IPC分类号： G06T7/00 , G06T19/20 , G06K9/34 , G06K9/00
CPC分类号： G06T7/0081 , G06K9/00228 , G06K9/342 , G06T7/11 , G06T7/174 , G06T7/194 , G06T7/74 , G06T19/20 , G06T2207/10012 , G06T2207/10024 , G06T2207/20221 , G06T2207/20224 , G06T2207/30196 , G06T2207/30201 , G06T2207/30244
摘要： Systems, devices and methods are described including receiving a source image having a foreground portion and a background portion, where the background portion includes image content of a three-dimensional (3D) environment. A camera pose of the source image may be determined by comparing features of the source image to image features of target images of the 3D environment and using the camera pose to segment the foreground portion from the background portion may generate a segmented source image. The resulting segmented source image and the associated camera pose may be stored in a networked database. The camera pose and segmented source image may be used to provide a simulation of the foreground portion in a virtual 3D environment.
摘要翻译：描述了系统，设备和方法，其包括接收具有前景部分和背景部分的源图像，其中背景部分包括三维（3D）环境的图像内容。源图像的相机姿态可以通过将源图像的特征与3D环境的目标图像的图像特征进行比较来确定，并且使用相机姿态来从背景部分分割前景部分可以生成分割的源图像。所产生的分割的源图像和相关联的摄像机姿态可以存储在联网的数据库中。相机姿态和分割的源图像可以用于在虚拟3D环境中提供前景部分的模拟。

8. 发明授权

US09106908B2 Video communication with three dimensional perception 有权
标题翻译：视频通信与三维感知
公开(公告)号：US09106908B2
公开(公告)日：2015-08-11
申请号：US13561131
申请日：2012-07-30
申请人： Yi Wu , Wei Sun , Michael M. Chu , Ermal Dreshaj , Philip Muse , Lucas B. Ainsworth , Garth Shoemaker , Igor V. Kozintsev
发明人： Yi Wu , Wei Sun , Michael M. Chu , Ermal Dreshaj , Philip Muse , Lucas B. Ainsworth , Garth Shoemaker , Igor V. Kozintsev
IPC分类号： H04N15/00 , H04N13/00 , H04N13/04 , H04N5/222 , H04N5/232
CPC分类号： H04N13/376 , G06T7/11 , G06T7/194 , G06T2207/10028 , H04N5/2226 , H04N5/23219 , H04N7/147 , H04N13/156 , H04N13/161 , H04N13/194 , H04N13/20 , H04N13/30 , H04N2013/0092 , H04N2213/006
摘要： Generally, this disclosure provides methods and systems for real-time video communication with three dimensional perception image rendering through generated parallax effects based on identification, segmentation and tracking of foreground and background layers of an image. The system may include an image segmentation module configured to segment a current local video frame into a local foreground layer and a local background layer and to generate a local foreground mask based on an estimated boundary between the local foreground layer and the local background layer; a face tracking module configured to track a position of a local user's face; a background layer estimation module configured to estimate a remote background layer; and an image rendering module configured to render a 3D perception image based on the estimated remote background layer, the current remote video frame and the remote foreground mask.
摘要翻译：通常，本公开提供了通过基于图像的前景和背景层的识别，分割和跟踪的生成的视差效应来实现具有三维感知图像呈现的实时视频通信的方法和系统。该系统可以包括图像分割模块，其被配置为将当前局部视频帧分割成本地前景层和本地背景层，并且基于本地前景层和本地背景层之间的估计边界来生成本地前景屏蔽; 面部跟踪模块，被配置为跟踪本地用户的脸部的位置; 配置为估计远程背景层的背景层估计模块; 以及图像渲染模块，被配置为基于估计的远程背景层，当前远程视频帧和远程前景掩码来渲染3D感知图像。

9. 发明授权

US09100980B2 Method, network element and system for scheduling communication link 有权
标题翻译：方法，网元和系统调度通信链路
公开(公告)号：US09100980B2
公开(公告)日：2015-08-04
申请号：US13583264
申请日：2010-03-08
申请人： Yi Wu , Hai Jiang
发明人： Yi Wu , Hai Jiang
IPC分类号： H04W72/12 , H04B7/26
CPC分类号： H04W72/1263 , H04B7/2656 , H04W72/1257
摘要： Provided is a method for scheduling a communication link, wherein the communication link is adapted for connecting two network elements, wherein a first carrier and a second carrier are assigned to the communication link, wherein each carrier includes frames divided into timeslots, and a predefined number of timeslots is allocated for downlink communication and a predefined number of timeslots is allocated for uplink communication. The method includes scheduling the communication link for offsetting the start of the frames of the first carrier in respect to the start of the frames of the second carrier. Also provided are a network element adapted for carrying out the method and a system including the network element.
摘要翻译：提供了一种用于调度通信链路的方法，其中通信链路适于连接两个网络元件，其中第一载波和第二载波被分配给通信链路，其中每个载波包括划分为时隙的帧和预定义的数字分配时隙用于下行链路通信，并且预定数量的时隙被分配用于上行链路通信。该方法包括调度通信链路，以相对于第二载波的帧的开始来抵消第一载波的帧的开始。还提供了适于执行该方法的网元和包括该网元的系统。

10. 发明授权

US08980215B2 Method for preparing ultrafine tungsten carbide powder 有权
标题翻译：超细碳化钨粉末制备方法
公开(公告)号：US08980215B2
公开(公告)日：2015-03-17
申请号：US13509621
申请日：2009-12-30
申请人： Baiwan Wei , Zhao Lin , Zhifeng Li , Anshi Zou , Yi Wu
发明人： Baiwan Wei , Zhao Lin , Zhifeng Li , Anshi Zou , Yi Wu
IPC分类号： C01B31/34 , C23C8/06
CPC分类号： C01B31/34 , C01B32/949
摘要： A method for preparing ultrafine powder of tungsten carbide using ultrafine tungsten powder and carbon black as raw materials is provided. The following steps are included: (1) passivation of the ultrafine tungsten powder: passivating the ultrafine tungsten powder under pure carbon dioxide; (2) carbon addition: mixing the ultrafine tungsten powder with carbon black powder after applying cooling water and inert gases; (3) carbonization: synthesizing the bulk tungsten carbide powder at high temperature in a carbonizing stove; (4) crushing and sieving: crushing the bulk tungsten carbide powder, cooling and sieving to obtain the ultrafine powder of tungsten carbide.
摘要翻译：提供了一种使用超细钨粉和炭黑作为原料制备碳化钨超细粉末的方法。包括以下步骤：（1）超细钨粉钝化：在纯二氧化碳下钝化超细钨粉; （2）碳添加：使用冷却水和惰性气体后，将超细钨粉与炭黑粉末混合; （3）碳化：在碳化炉中高温合成本体碳化钨粉末; （4）破碎筛分：粉碎散装碳化钨粉末，冷却筛分得到超细碳化钨粉末。

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