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. 发明申请

US20110191271A1 IMAGE TAGGING BASED UPON CROSS DOMAIN CONTEXT 有权
标题翻译：基于跨域语言的图像标签
公开(公告)号：US20110191271A1
公开(公告)日：2011-08-04
申请号：US12699889
申请日：2010-02-04
申请人： Simon John Baker , Ashish Kapoor , Gang Hua , Dahua Lin
发明人： Simon John Baker , Ashish Kapoor , Gang Hua , Dahua Lin
IPC分类号： G06N5/02 , G06F15/18
CPC分类号： G06N5/04 , G06F3/04842 , G06K9/00677 , G06K9/72 , G06Q10/10
摘要： A method described herein includes receiving a digital image, wherein the digital image includes a first element that corresponds to a first domain and a second element that corresponds to a second domain. The method also includes automatically assigning a label to the first element in the digital image based at least in part upon a computed probability that the label corresponds to the first element, wherein the probability is computed through utilization of a first model that is configured to infer labels for elements in the first domain and a second model that is configured to infer labels for elements in the second domain. The first model receives data that identifies learned relationships between elements in the first domain and elements in the second domain, and the probability is computed by the first model based at least in part upon the learned relationships.
摘要翻译：本文所述的方法包括接收数字图像，其中所述数字图像包括对应于第一域的第一元素和对应于第二域的第二元素。该方法还包括至少部分地基于计算出的标签对应于第一元素的概率来自动地将标签分配给数字图像中的第一元素，其中通过利用被配置为推断的第一模型来计算概率第一个域中的元素的标签以及被配置为推断第二个域中的元素的标签的第二个模型。第一模型接收识别第一域中的元素和第二域中的元素之间的学习关系的数据，并且该概率由至少部分地基于学习关系的第一模型计算。

2. 发明授权

US08645287B2 Image tagging based upon cross domain context 有权
标题翻译：基于跨域上下文的图像标记
公开(公告)号：US08645287B2
公开(公告)日：2014-02-04
申请号：US12699889
申请日：2010-02-04
申请人： Simon John Baker , Ashish Kapoor , Gang Hua , Dahua Lin
发明人： Simon John Baker , Ashish Kapoor , Gang Hua , Dahua Lin
IPC分类号： G06F17/00
CPC分类号： G06N5/04 , G06F3/04842 , G06K9/00677 , G06K9/72 , G06Q10/10
摘要： A method described herein includes receiving a digital image, wherein the digital image includes a first element that corresponds to a first domain and a second element that corresponds to a second domain. The method also includes automatically assigning a label to the first element in the digital image based at least in part upon a computed probability that the label corresponds to the first element, wherein the probability is computed through utilization of a first model that is configured to infer labels for elements in the first domain and a second model that is configured to infer labels for elements in the second domain. The first model receives data that identifies learned relationships between elements in the first domain and elements in the second domain, and the probability is computed by the first model based at least in part upon the learned relationships.
摘要翻译：本文所述的方法包括接收数字图像，其中所述数字图像包括对应于第一域的第一元素和对应于第二域的第二元素。该方法还包括至少部分地基于计算出的标签对应于第一元素的概率来自动地将标签分配给数字图像中的第一元素，其中通过利用被配置为推断的第一模型来计算概率第一个域中的元素的标签以及被配置为推断第二个域中的元素的标签的第二个模型。第一模型接收识别第一域中的元素和第二域中的元素之间的学习关系的数据，并且该概率由至少部分地基于学习关系的第一模型计算。

3. 发明授权

US08325999B2 Assisted face recognition tagging 有权
标题翻译：辅助面部识别标记
公开(公告)号：US08325999B2
公开(公告)日：2012-12-04
申请号：US12479879
申请日：2009-06-08
申请人： Ashish Kapoor , Gang Hua , Amir Akbarzadeh , Simon J. Baker
发明人： Ashish Kapoor , Gang Hua , Amir Akbarzadeh , Simon J. Baker
IPC分类号： G06K9/00
CPC分类号： G06K9/72 , G06K9/00288 , G06K9/6254 , G06K2209/27
摘要： The described implementations relate to assisted face recognition tagging of digital images, and specifically to context-driven assisted face recognition tagging. In one case, context-driven assisted face recognition tagging (CDAFRT) tools can access face images associated with a photo gallery. The CDAFRT tools can perform context-driven face recognition to identify individual face images at a specified probability. In such a configuration, the probability that the individual face images are correctly identified can be higher than attempting to identify individual face images in isolation.
摘要翻译：所描述的实现涉及数字图像的辅助面部识别标记，并且具体涉及上下文驱动的辅助人脸识别标签。在一种情况下，上下文驱动的辅助人脸识别标签（CDAFRT）工具可以访问与照片库相关联的面部图像。 CDAFRT工具可以执行上下文驱动的面部识别，以指定的概率识别个人脸部图像。在这种配置中，个体面部图像被正确识别的概率可以高于孤立地识别个人脸部图像的概率。

4. 发明申请

US20100310134A1 ASSISTED FACE RECOGNITION TAGGING 有权
标题翻译：辅助面部识别标签
公开(公告)号：US20100310134A1
公开(公告)日：2010-12-09
申请号：US12479879
申请日：2009-06-08
申请人： Ashish Kapoor , Gang Hua , Amir Akbarzadeh , Simon J. Baker
发明人： Ashish Kapoor , Gang Hua , Amir Akbarzadeh , Simon J. Baker
IPC分类号： G06K9/00
CPC分类号： G06K9/72 , G06K9/00288 , G06K9/6254 , G06K2209/27
摘要： The described implementations relate to assisted face recognition tagging of digital images, and specifically to context-driven assisted face recognition tagging. In one case, context-driven assisted face recognition tagging (CDAFRT) tools can access face images associated with a photo gallery. The CDAFRT tools can perform context-driven face recognition to identify individual face images at a specified probability. In such a configuration, the probability that the individual face images are correctly identified can be higher than attempting to identify individual face images in isolation.
摘要翻译：所描述的实现涉及数字图像的辅助面部识别标记，并且具体涉及上下文驱动的辅助人脸识别标签。在一种情况下，上下文驱动的辅助人脸识别标签（CDAFRT）工具可以访问与照片库相关联的面部图像。 CDAFRT工具可以执行上下文驱动的面部识别，以指定的概率识别个人脸部图像。在这种配置中，个体面部图像被正确识别的概率可以高于孤立地识别个人脸部图像的概率。

5. 发明授权

US09122995B2 Classification of stream-based data using machine learning 有权
标题翻译：使用机器学习分析基于流的数据
公开(公告)号：US09122995B2
公开(公告)日：2015-09-01
申请号：US13047804
申请日：2011-03-15
申请人： Bongshin Lee , Ashish Kapoor , Ratul Mahajan , Blaine S. Christian , Saleema Amershi
发明人： Bongshin Lee , Ashish Kapoor , Ratul Mahajan , Blaine S. Christian , Saleema Amershi
IPC分类号： G06N99/00
CPC分类号： G06N99/005
摘要： The described implementations relate to data classification. One implementation includes identifying one or more likely classifications for an incoming data item using an algorithm. The implementation can also include providing the one or more identified classifications to a user. A selection of an individual identified classification for the incoming data item can be received from the user. The algorithm can be refined to reflect the selection by the user.
摘要翻译：所描述的实现涉及数据分类。一个实现包括使用算法识别输入数据项的一个或多个可能的分类。该实现还可以包括向用户提供一个或多个所识别的分类。可以从用户接收对输入数据项目的单独识别的分类的选择。该算法可以被细化以反映用户的选择。

6. 发明申请

US20110292162A1 NON-LINGUISTIC SIGNAL DETECTION AND FEEDBACK 有权
标题翻译：非线性信号检测和反馈
公开(公告)号：US20110292162A1
公开(公告)日：2011-12-01
申请号：US12789142
申请日：2010-05-27
申请人： Byungki Byun , Philip A. Chou , Mary P. Czerwinski , Ashish Kapoor , Bongshin Lee
发明人： Byungki Byun , Philip A. Chou , Mary P. Czerwinski , Ashish Kapoor , Bongshin Lee
IPC分类号： H04N7/14
CPC分类号： H04N7/15 , H04N7/147
摘要： Non-linguistic signal information relating to one or more participants to an interaction may be determined using communication data received from the one or more participants. Feedback can be provided based on the determined non-linguistic signals. The participants may be given an opportunity to opt in to having their non-linguistic signal information collected, and may be provided complete control over how their information is shared or used.
摘要翻译：可以使用从一个或多个参与者接收的通信数据来确定与交互的一个或多个参与者有关的非语言信号信息。可以基于确定的非语言信号提供反馈。参与者可能有机会选择收集其非语言信号信息，并且可以完全控制他们的信息如何共享或使用。

7. 发明申请

US20110251980A1 Interactive Optimization of the Behavior of a System 有权
标题翻译：交互式优化系统的行为
公开(公告)号：US20110251980A1
公开(公告)日：2011-10-13
申请号：US12756183
申请日：2010-04-08
申请人： Ashish Kapoor , Bongshin Lee , Desney S. Tan , Eric J. Horvitz
发明人： Ashish Kapoor , Bongshin Lee , Desney S. Tan , Eric J. Horvitz
IPC分类号： G06F15/18 , G06N5/02 , G06F1/24
CPC分类号： G06N99/005
摘要： An interactive tool is described for modifying the behavior of a system, such as, but not limited to, the behavior of a classification system. The tool uses an interface mechanism to present a current global state of the system. The tool accepts one or more refinements to this global state, e.g., by accepting individual changes to parameter settings that are presented by the interface mechanism. Based on this input, the tool computes and displays the global implications of the updated parameter settings. The process of iterating over one or more cycles of user updates, followed by computation and display of the implications of the attempted refinements, has the effect of advancing the system towards a global state that exhibits desirable behavior.
摘要翻译：描述了用于修改系统的行为的交互式工具，例如但不限于分类系统的行为。该工具使用接口机制来呈现系统的当前全局状态。该工具接受对该全局状态的一个或多个改进，例如通过接受由接口机制呈现的参数设置的单独改变。基于此输入，该工具计算并显示更新参数设置的全局含义。迭代一个或多个用户更新周期的过程，随后计算和显示尝试改进的含义，具有将系统推向呈现期望行为的全局状态的效果。

8. 发明申请

US20100241596A1 INTERACTIVE VISUALIZATION FOR GENERATING ENSEMBLE CLASSIFIERS 有权
标题翻译：用于生成ENSEMBLE分类器的交互式可视化
公开(公告)号：US20100241596A1
公开(公告)日：2010-09-23
申请号：US12408663
申请日：2009-03-20
申请人： Bongshin Lee , Ashish Kapoor , Desney Tan , Justin Talbot
发明人： Bongshin Lee , Ashish Kapoor , Desney Tan , Justin Talbot
IPC分类号： G06F17/00 , G06F15/18 , G06N5/02
CPC分类号： G06N99/005
摘要： A real-time visual feedback ensemble classifier generator and method for interactively generating an optimal ensemble classifier using a user interface. Embodiments of the real-time visual feedback ensemble classifier generator and method use a weight adjustment operation and a partitioning operation in the interactive generation process. In addition, the generator and method include a user interface that provides real-time visual feedback to a user so that the user can see how the weight adjustment and partitioning operation affect the overall accuracy of the ensemble classifier. Using the user interface and the interactive controls available on the user interface, a user can iteratively use one or both of the weigh adjustment operation and partitioning operation to generate an optimized ensemble classifier.
摘要翻译：一种实时视觉反馈综合分类器生成器和方法，用于使用用户界面交互式生成最佳集合分类器。实时视觉反馈综合分类器发生器和方法的实施例在交互式生成过程中使用权重调整操作和分割操作。此外，发生器和方法包括向用户提供实时视觉反馈的用户界面，使得用户可以看到权重调整和分割操作如何影响整体分类器的整体精度。使用用户界面上的用户界面和交互式控件，用户可以迭代地使用权重调整操作和分区操作中的一个或两者来生成优化的整体分类器。

9. 发明授权

US07727339B2 Submerged arc flux 有权
标题翻译：埋弧焊
公开(公告)号：US07727339B2
公开(公告)日：2010-06-01
申请号：US11144423
申请日：2005-06-06
申请人： Ashish Kapoor , Teresa A. Melfi
发明人： Ashish Kapoor , Teresa A. Melfi
IPC分类号： B23K35/34 , B23K35/24
CPC分类号： B23K35/362 , B23K35/36 , B23K35/3601 , B23K35/3605 , B23K35/3607
摘要： A highly basic particle flux for submerged arc welding that produces less than 7 ml/100 gr of diffusible hydrogen in the weld metal, which flux comprises a carbon dioxide containing compound with an effective amount of heat releasable carbon dioxide in the range of 0.5-3.5% by weight of the flux over 10% by weight of a low melting point compound and a binder.
摘要翻译：用于埋弧焊的高度基本的颗粒通量，其在焊缝金属中产生小于7ml / 100gr的可扩散氢，该焊剂包含含二氧化碳的化合物，其中有效量的可热释放的二氧化碳的范围为0.5-3.5 通量超过10重量％的低熔点化合物和粘合剂的重量％。

10. 发明申请

US20090154795A1 INTERACTIVE CONCEPT LEARNING IN IMAGE SEARCH 有权
标题翻译：图像搜索中的交互式概念学习
公开(公告)号：US20090154795A1
公开(公告)日：2009-06-18
申请号：US11954246
申请日：2007-12-12
申请人： Desney S. Tan , Ashish Kapoor , Simon A. J. Winder , James A. Fogarty
发明人： Desney S. Tan , Ashish Kapoor , Simon A. J. Winder , James A. Fogarty
IPC分类号： G06K9/62
CPC分类号： G06F17/30247 , G06K9/6215
摘要： An interactive concept learning image search technique that allows end-users to quickly create their own rules for re-ranking images based on the image characteristics of the images. The image characteristics can include visual characteristics as well as semantic features or characteristics, or may include a combination of both. End-users can then rank or re-rank any current or future image search results according to their rule or rules. End-users provide examples of images each rule should match and examples of images the rule should reject. The technique learns the common image characteristics of the examples, and any current or future image search results can then be ranked or re-ranked according to the learned rules.
摘要翻译：一种交互式概念学习图像搜索技术，允许最终用户基于图像的图像特征快速创建自己的重新排序图像的规则。图像特征可以包括视觉特征以及语义特征或特征，或者可以包括两者的组合。然后，最终用户可以根据其规则或规则对当前或将来的图像搜索结果进行排名或重新排序。最终用户提供每个规则应该匹配的图像的示例以及规则应该拒绝的图像的示例。该技术学习示例的常见图像特征，然后可以根据学习的规则对任何当前或将来的图像搜索结果进行排名或重新排序。

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