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

US08326820B2 Long-query retrieval 有权
标题翻译：长查询检索
公开(公告)号：US08326820B2
公开(公告)日：2012-12-04
申请号：US12571302
申请日：2009-09-30
申请人： Zhiwei Li , Lei Zhang , Rui Cai , Wei-Ying Ma , Heung-Yeung Shum
发明人： Zhiwei Li , Lei Zhang , Rui Cai , Wei-Ying Ma , Heung-Yeung Shum
IPC分类号： G06F17/30
CPC分类号： G06F17/3028 , G06F17/30448
摘要： Described herein is a technology that facilitates efficient large-scale similarity-based retrieval. In several embodiments documents, images, and/or other multimedia files are compactly represented and efficiently indexed to enable robust search using a long-query in a large-scale corpus. As described herein, these techniques include performing decomposition of a file, e.g., a document or document-like representation. The techniques use dimension reduction to obtain three parts, topic-related words (major semantics), document specific words (minor semantics), and background words, representing the major semantics in a feature vector and the minor semantics as keywords. Using the techniques described, file vectors are matched in a topic model and the results ranked based on the keywords.
摘要翻译：这里描述了一种有助于有效的大规模相似性检索的技术。在几个实施例中，文档，图像和/或其他多媒体文件被紧凑地表示并且被有效地索引，以使得能够使用大规模语料库中的长查询进行鲁棒搜索。如这里所述，这些技术包括执行文件的分解，例如文档或类似文档的表示。这些技术使用维度缩减来获得三个部分，主题相关词（主要语义），文档特定词（次要语义）和背景词，表示特征向量中的主要语义和次要语义作为关键字。使用所描述的技术，在主题模型中匹配文件向量，并根据关键字对结果进行排名。

2. 发明申请

US20110078159A1 Long-Query Retrieval 有权
标题翻译：长查询检索
公开(公告)号：US20110078159A1
公开(公告)日：2011-03-31
申请号：US12571302
申请日：2009-09-30
申请人： Zhiwei Li , Lei Zhang , Rui Cai , Wei-Ying Ma , Heung-Yeung Shum
发明人： Zhiwei Li , Lei Zhang , Rui Cai , Wei-Ying Ma , Heung-Yeung Shum
IPC分类号： G06F17/30
CPC分类号： G06F17/3028 , G06F17/30448
摘要： Described herein is a technology that facilitates efficient large-scale similarity-based retrieval. In several embodiments documents, images, and/or other multimedia files are compactly represented and efficiently indexed to enable robust search using a long-query in a large-scale corpus. As described herein, these techniques include performing decomposition of a file, e.g., a document or document-like representation. The techniques use dimension reduction to obtain three parts, topic-related words (major semantics), document specific words (minor semantics), and background words, representing the major semantics in a feature vector and the minor semantics as keywords. Using the techniques described, file vectors are matched in a topic model and the results ranked based on the keywords.
摘要翻译：这里描述了一种有助于有效的大规模相似性检索的技术。在几个实施例中，文档，图像和/或其他多媒体文件被紧凑地表示并且被有效地索引，以使得能够使用大规模语料库中的长查询进行鲁棒搜索。如这里所述，这些技术包括执行文件的分解，例如文档或类似文档的表示。这些技术使用维度缩减来获得三个部分，主题相关词（主要语义），文档特定词（次要语义）和背景词，表示特征向量中的主要语义和次要语义作为关键字。使用所描述的技术，在主题模型中匹配文件向量，并根据关键字对结果进行排名。

3. 发明申请

US20090006189A1 DISPLAYING OF ADVERTISEMENT-INFUSED THUMBNAILS OF IMAGES 审中-公开
标题翻译：显示广告投放图像的图像
公开(公告)号：US20090006189A1
公开(公告)日：2009-01-01
申请号：US11769518
申请日：2007-06-27
申请人： Lei Zhang , Wei-Ying Ma , Ruochi Zhang , Zhiwei Li , Hsiao-Wuen Hon , Heung-Yeung Shum
发明人： Lei Zhang , Wei-Ying Ma , Ruochi Zhang , Zhiwei Li , Hsiao-Wuen Hon , Heung-Yeung Shum
IPC分类号： G06Q30/00
CPC分类号： G06Q30/02 , G06Q30/0247 , G06Q30/0277
摘要： An image advertisement system of a computing device displays as part of a display page an advertisement-infused thumbnail of an image prior to displaying the image. The image advertisement system initially receives a display page with an indication of an image to be displayed as part of the display page. The image advertisement system generates an advertisement-infused thumbnail of the image by combining advertisement content with a thumbnail of the image. The image advertisement system then displays the display page with the advertisement-infused thumbnail of the image in place of the image. The image advertisement system then replaces the displayed advertisement-infused thumbnail with the image.
摘要翻译：计算设备的图像广告系统在显示图像之前，将图像的广告注入的缩略图显示为显示页面的一部分。图像广告系统最初接收具有作为显示页面的一部分显示的图像的指示的显示页面。图像广告系统通过将广告内容与图像的缩略图组合来生成图像的广告注入的缩略图。图像广告系统然后显示具有图像的广告输入的缩略图的显示页面来代替图像。然后，图像广告系统用图像代替显示的广告输入的缩略图。

4. 发明授权

US08773423B2 Creating optimized gradient mesh of a vector-based image from a raster-based image 有权
标题翻译：从基于光栅的图像创建基于矢量的图像的优化梯度网格
公开(公告)号：US08773423B2
公开(公告)日：2014-07-08
申请号：US11800680
申请日：2007-05-07
申请人： Jian Sun , Lin Liang , Fang Wen , Heung-Yeung Shum
发明人： Jian Sun , Lin Liang , Fang Wen , Heung-Yeung Shum
IPC分类号： G06T15/00
CPC分类号： G06T17/20
摘要： A method for creating an optimized gradient mesh of a vector-based image from a raster-based image. In one implementation, a set of boundaries for an object on a raster-based image may be received. An initial gradient mesh of the object may be created. A residual energy between the object on the raster-based image and a rendered initial gradient mesh may be minimized to generate an optimized gradient mesh.
摘要翻译：一种用于从基于光栅的图像创建基于矢量的图像的优化梯度网格的方法。在一个实现中，可以接收基于光栅的图像上的对象的一组边界。可以创建对象的初始渐变网格。基于光栅的图像上的对象与渲染的初始梯度网格之间的剩余能量可以被最小化以生成优化的梯度网格。

5. 发明授权

US08498455B2 Scalable face image retrieval 有权
标题翻译：可扩展的面部图像检索
公开(公告)号：US08498455B2
公开(公告)日：2013-07-30
申请号：US12792750
申请日：2010-06-03
申请人： Qifa Ke , Yi Li , Heung-Yeung Shum , Jian Sun , Zhong Wu
发明人： Qifa Ke , Yi Li , Heung-Yeung Shum , Jian Sun , Zhong Wu
IPC分类号： G06K9/00
CPC分类号： G06K9/4676 , G06K9/00281
摘要： A system for identifying individuals in digital images and for providing matching digital images is provided. A set of images that include faces of known individuals is received. Faces are detected in the images and facial components are identified in each face. Visual words corresponding to the facial components are generated, stored, and associated with identifiers of the individuals. At a later time, a user may provide an image that includes the face of one of the known individuals. Visual words are determined from the face of the individual in the provided image and matched against the stored visual words. Images associated with matching visual words are ranked and presented to the user.
摘要翻译：提供了一种用于识别数字图像中的个体并提供匹配的数字图像的系统。接收包括已知个人面孔的一组图像。在图像中检测到面部，并且在每个面部中识别面部组件。对应于面部组件的视觉词被生成，存储并与个人的标识符相关联。在稍后的时间，用户可以提供包括已知个体之一的脸部的图像。视觉词是从提供的图像中的个体的脸部确定的，并且与存储的视觉词匹配。与匹配的视觉词相关联的图像被排序并呈现给用户。

6. 发明申请

US20120233209A1 ENTERPRISE SEARCH OVER PRIVATE AND PUBLIC DATA 有权
标题翻译：企业在私人和公共数据中搜索
公开(公告)号：US20120233209A1
公开(公告)日：2012-09-13
申请号：US13044414
申请日：2011-03-09
申请人： Lili Cheng , Xuedong David Huang , Heung-Yeung Shum , Erik J. Horvitz , James H. Lewallen , Todd D. Newman , David S. Taniguchi
发明人： Lili Cheng , Xuedong David Huang , Heung-Yeung Shum , Erik J. Horvitz , James H. Lewallen , Todd D. Newman , David S. Taniguchi
IPC分类号： G06F17/30 , G06F15/16
CPC分类号： G06F17/30312
摘要： A unified search service may collect information related to an enterprise from at least one of publicly available data and private enterprise data. In some implementations, crowd sourcing may be used to determine a source list of one or more sources of information. Authored content can be generated, such as by combining one or more items of information from the public data with one or more items of information from the private enterprise data. Further, in some implementations, a public index may be generated from the public data, and one or more affiliation indexes may be generated from the private enterprise data. For example, a first affiliation index may contain confidential enterprise information, while a second affiliation index may contain non-confidential enterprise information. A user's affiliation to the enterprise may be taken into consideration when determining which indexes to use when responding to a search request from the user.
摘要翻译：统一搜索服务可以从公开数据和私有企业数据中的至少一个收集与企业相关的信息。在一些实施方式中，群体来源可用于确定一个或多个信息源的源列表。可以生成创作内容，例如通过将来自公共数据的一个或多个信息项目与来自私人企业数据的一个或多个信息项组合。此外，在一些实现中，可以从公共数据生成公共索引，并且可以从私有企业数据生成一个或多个附属索引。例如，第一附属索引可以包含机密企业信息，而第二隶属关系索引可以包含非机密企业信息。当确定在响应来自用户的搜索请求时使用哪些索引时，可以考虑用户与企业的联系。

7. 发明授权

US08190403B2 Real-time rendering of light-scattering media 有权
标题翻译：实时渲染光散射介质
公开(公告)号：US08190403B2
公开(公告)日：2012-05-29
申请号：US11830794
申请日：2007-07-30
申请人： Kun Zhou , Zhong Ren , Stephen Ssu-te Lin , Baining Guo , Heung-Yeung Shum
发明人： Kun Zhou , Zhong Ren , Stephen Ssu-te Lin , Baining Guo , Heung-Yeung Shum
IPC分类号： G06F17/10
CPC分类号： G06T15/55
摘要： A real-time algorithm for rendering of an inhomogeneous scattering media such as smoke under dynamic low-frequency environment lighting is described. An input media animation is represented as a sequence of density fields, each of which is decomposed into a weighted sum of a set of radial basis functions (RBFs) and an optional residual field. Source radiances from single and optionally multiple scattering are directly computed at only the RBF centers and then approximated at other points in the volume using an RBF-based interpolation. Unique approximation techniques are introduced in the computational algorithms to simplify and speed up the computation of source radiance contributed by single and multiple scattering. Using the computed source radiances, a ray marching technique using slice-based integration of radiance along each viewing ray may be performed to render the final image.
摘要翻译：描述了在动态低频环境照明下渲染非均匀散射介质（如烟雾）的实时算法。输入媒体动画被表示为密度字段序列，每个密度字段被分解成一组径向基函数（RBF）和可选残余字段的加权和。仅从RBF中心直接计算来自单个和任选多个散射的源辐射，然后使用基于RBF的插值在体积中的其他点处近似。在计算算法中引入了独特的近似技术，以简化和加快由单次和多次散射贡献的源辐射的计算。使用计算的源辐射，可以执行使用沿着每个观察射线的基于片段的辐射积分的射线行进技术来渲染最终图像。

8. 发明申请

US20110299743A1 SCALABLE FACE IMAGE RETRIEVAL 有权
标题翻译：可扩展的脸部图像检索
公开(公告)号：US20110299743A1
公开(公告)日：2011-12-08
申请号：US12792750
申请日：2010-06-03
申请人： Qifa Ke , Yi Li , Heung-Yeung Shum , Jian Sun , Zhong Wu
发明人： Qifa Ke , Yi Li , Heung-Yeung Shum , Jian Sun , Zhong Wu
IPC分类号： G06T7/00
CPC分类号： G06K9/4676 , G06K9/00281
摘要： A system for identifying individuals in digital images and for providing matching digital images is provided. A set of images that include faces of known individuals is received. Faces are detected in the images and facial components are identified in each face. Visual words corresponding to the facial components are generated, stored, and associated with identifiers of the individuals. At a later time, a user may provide an image that includes the face of one of the known individuals. Visual words are determined from the face of the individual in the provided image and matched against the stored visual words. Images associated with matching visual words are ranked and presented to the user.
摘要翻译：提供了一种用于识别数字图像中的个体并提供匹配的数字图像的系统。接收包括已知个人面孔的一组图像。在图像中检测到面部，并且在每个面部中识别面部组件。对应于面部组件的视觉词被生成，存储并与个人的标识符相关联。在稍后的时间，用户可以提供包括已知个体之一的脸部的图像。视觉词是从提供的图像中的个体的脸部确定的，并且与存储的视觉词匹配。与匹配视觉词相关联的图像被排序并呈现给用户。

9. 发明授权

US07640502B2 Presentation facilitation 有权
标题翻译：简报介绍
公开(公告)号：US07640502B2
公开(公告)日：2009-12-29
申请号：US10957037
申请日：2004-10-01
申请人： Ying-Qing Xu , Heung-Yeung Shum , Ya-Qin Zhang , Barn-Wan Li , Bo Liu
发明人： Ying-Qing Xu , Heung-Yeung Shum , Ya-Qin Zhang , Barn-Wan Li , Bo Liu
IPC分类号： G06F3/00 , G06F3/048
CPC分类号： G06F3/1423 , G06F3/0481 , G06F3/04842 , G06F2203/04803 , G06Q10/10
摘要： Multiple schemes and techniques for facilitating presentations with an interactive application are described. For example, an interactive application provides a console view overlay for integrating multiple productivity applications into a graphical user interface (GUI) window. An interactive application can also share a selected display portion of the console view overlay with other interactive applications. As another example, presenters and other audience members can draw on the selected display portion being shared, and the drawn graphics are synchronously displayed by the other interactive applications. Interactive applications, as directed by their users, can join various member groups and specific presentations thereof. Moreover, a user may share content in accordance with membership grouping.
摘要翻译：描述了用于促进与交互应用的呈现的多种方案和技术。例如，交互式应用程序提供了一个控制台视图覆盖，用于将多个生产力应用程序集成到图形用户界面（GUI）窗口中。交互式应用程序还可以与其他交互式应用程序共享控制台视图覆盖的选定显示部分。作为另一示例，演示者和其他观众成员可以在所选择的显示部分上进行共享，并且绘制的图形被其他交互式应用程序同步显示。按照用户的指示，交互式应用程序可以加入各种成员组及其具体演示。此外，用户可以根据会员分组来共享内容。

10. 发明授权

US07633511B2 Pop-up light field 有权
标题翻译：弹出光场
公开(公告)号：US07633511B2
公开(公告)日：2009-12-15
申请号：US10817516
申请日：2004-04-01
申请人： Heung-Yeung Shum , Jian Sun , Shuntaro Yamazaki , Yin Li
发明人： Heung-Yeung Shum , Jian Sun , Shuntaro Yamazaki , Yin Li
IPC分类号： G09G5/00
CPC分类号： G06T15/205
摘要： Virtual views of a complex scene are produced for a user to view. The virtual views are substantially free from aliasing even when using a relatively sparse set of images of the scene. In a described implementation, a scene is split into one or more coherent layers. The boundaries of the coherent layers are propagated across a plurality of frames corresponding to the scene. The splitting may be further refined (e.g., in accordance with user feedback) to present a virtual view of the scene.
摘要翻译：生成复杂场景的虚拟视图，供用户查看。即使当使用场景的相对稀疏的图像集时，虚拟视图也基本上没有混叠。在所描述的实现中，场景被分成一个或多个相干层。相干层的边界跨越对应于场景的多个帧传播。可以进一步改进分割（例如，根据用户反馈）来呈现场景的虚拟视图。

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