专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明申请

US20100114888A1 DIGITAL IMAGE RETRIEVAL BY AGGREGATING SEARCH RESULTS BASED ON VISUAL ANNOTATIONS 有权
标题翻译：通过视觉观察聚合搜索结果的数字图像检索
公开(公告)号：US20100114888A1
公开(公告)日：2010-05-06
申请号：US12258349
申请日：2008-10-24
申请人： Roelof van Zwol , Ximena Olivares
发明人： Roelof van Zwol , Ximena Olivares
IPC分类号： G06F17/30
CPC分类号： G06F17/30265
摘要： An approach for responding to a text-based query for a digital image is provided. A request that identifies one or more keywords is received. A number of annotated digital images are selected. Each selected annotated digital image has a bounded region, on its appearance, that has an annotation associated with at least one of the keywords. A set of candidate digital images is selected for each annotated digital image. The set of candidate images, for a particular annotated digital image, are the digital images, of a set of digital images, which have an appearance that is most similar to the particular annotated digital image. The sets of candidate images are aggregated into a single set of digital images. A response is generated that identifies those digital images in the single set of digital images which are most responsive to the one or more keywords.
摘要翻译：提供了一种用于响应数字图像的基于文本的查询的方法。接收到识别一个或多个关键字的请求。选择了许多带注释的数字图像。每个选择的注释数字图像具有在其外观上具有与至少一个关键字相关联的注释的有界区域。为每个带注释的数字图像选择一组候选数字图像。用于特定注释数字图像的候选图像集合是一组数字图像的数字图像，其具有与特定注释数字图像最相似的外观。候选图像的集合被聚合成单个数字图像集合。产生响应，其识别对一个或多个关键词最响应的单个数字图像集合中的那些数字图像。

42. 发明申请

US20090063449A1 Integrating Sponsored Media with User-Generated Content 有权
标题翻译：将赞助媒体与用户生成的内容整合
公开(公告)号：US20090063449A1
公开(公告)日：2009-03-05
申请号：US11846786
申请日：2007-08-29
申请人： Roelof van Zwol
发明人： Roelof van Zwol
IPC分类号： G06F17/30
CPC分类号： G06Q30/0251 , G06F3/0481 , G06F17/211 , G06F17/30056 , H04L65/602 , H04L65/607
摘要： A variety of computer based service that permit users to edit, compose, upload, or otherwise generate content also provide for the integration of sponsored media into presentations along with user-generated content. An exemplary service generates text based on user input, provides tags based on the text to a sponsored media repository, receives a sponsored media data structure in return, and formats sponsored media from the data structure for display to the user.
摘要翻译：允许用户编辑，撰写，上传或以其他方式生成内容的各种基于计算机的服务还提供将赞助媒体与用户生成的内容一起集成到演示文稿中。示例性服务基于用户输入生成文本，将基于文本的标签提供给赞助的媒体库，作为回报接收赞助的媒体数据结构，并且从所述数据结构格式化用于显示的用户的赞助媒体。

43. 发明授权

US09137574B2 Method or system to predict media content preferences 有权
标题翻译：预测媒体内容偏好的方法或系统
公开(公告)号：US09137574B2
公开(公告)日：2015-09-15
申请号：US12845684
申请日：2010-07-28
申请人： Adam Rae , Lluis Garcia Pueyo , Roelof van Zwol
发明人： Adam Rae , Lluis Garcia Pueyo , Roelof van Zwol
IPC分类号： H04N21/466 , G06F17/30 , H04N21/45 , H04N21/482
CPC分类号： H04N21/466 , G06F17/30268 , G06F17/30274 , H04N21/4532 , H04N21/482
摘要： Briefly, embodiments of a method or system of predicting media content preferences are disclosed.
摘要翻译：简而言之，公开了预测媒体内容偏好的方法或系统的实施例。

44. 发明授权

US08938116B2 Image cropping using supervised learning 有权
标题翻译：使用监督学习的图像裁剪
公开(公告)号：US08938116B2
公开(公告)日：2015-01-20
申请号：US13315066
申请日：2011-12-08
申请人： Lyndon Kennedy , Roelof van Zwol , Nicolas Torzec , Belle Tseng
发明人： Lyndon Kennedy , Roelof van Zwol , Nicolas Torzec , Belle Tseng
IPC分类号： G06K9/62
CPC分类号： G06K9/00711 , G06K9/00228 , G06K9/46 , G06K9/4671 , G06K9/52 , G06K9/62 , G06K9/6201 , G06K2009/4666 , G06T3/40 , G06T11/60
摘要： Software for supervised learning extracts a set of pixel-level features from each source image in collection of source images. Each of the source images is associated with a thumbnail created by an editor. The software also generates a collection of unique bounding boxes for each source image. And the software calculates a set of region-level features for each bounding box. Each region-level feature results from the aggregation of pixel values for one of the pixel-level features. The software learns a regression model, using the calculated region-level features and the thumbnail associated with the source image. Then the software chooses a thumbnail from a collection of unique bounding boxes in a new image, based on application of the regression model.
摘要翻译：用于监督学习的软件在收集源图像时从每个源图像中提取一组像素级特征。每个源图像与由编辑器创建的缩略图相关联。该软件还为每个源图像生成一组独特的边界框。并且软件为每个边界框计算一组区域级别的功能。每个区域级别的特征来自于像素级特征之一的像素值的聚合。该软件学习回归模型，使用计算的区域级功能和与源图像相关联的缩略图。然后，软件根据回归模型的应用，从新图像中的独特边界框的集合中选择一个缩略图。

45. 发明授权

US08639714B2 Integrating sponsored media with user-generated content 有权
标题翻译：将赞助媒体与用户生成的内容集成
公开(公告)号：US08639714B2
公开(公告)日：2014-01-28
申请号：US11846786
申请日：2007-08-29
申请人： Roelof van Zwol
发明人： Roelof van Zwol
IPC分类号： G06F17/30
CPC分类号： G06Q30/0251 , G06F3/0481 , G06F17/211 , G06F17/30056 , H04L65/602 , H04L65/607
摘要： A variety of computer based service that permit users to edit, compose, upload, or otherwise generate content also provide for the integration of sponsored media into presentations along with user-generated content. An exemplary service generates text based on user input, provides tags based on the text to a sponsored media repository, receives a sponsored media data structure in return, and formats sponsored media from the data structure for display to the user.
摘要翻译：允许用户编辑，撰写，上传或以其他方式生成内容的各种基于计算机的服务还提供将赞助媒体与用户生成的内容一起集成到演示文稿中。示例性服务基于用户输入生成文本，将基于文本的标签提供给赞助的媒体库，作为回报接收赞助的媒体数据结构，并且从所述数据结构格式化用于显示的用户的赞助媒体。

46. 发明授权

US08634654B2 Logo or image recognition 有权
标题翻译：标识或图像识别
公开(公告)号：US08634654B2
公开(公告)日：2014-01-21
申请号：US13088305
申请日：2011-04-15
申请人： Roelof van Zwol , Luis Garcia Pueyo , Stefan Romberg
发明人： Roelof van Zwol , Luis Garcia Pueyo , Stefan Romberg
IPC分类号： G06K9/46
CPC分类号： G06K9/6202 , G06K9/6211
摘要： Subject matter disclosed herein relates to electronic image object or logo recognition.
摘要翻译：本文公开的主题涉及电子图像对象或标识识别。

47. 发明申请

US20130142418A1 RANKING AND SELECTING REPRESENTATIVE VIDEO IMAGES 有权
标题翻译：排名和选择代表性视频图像
公开(公告)号：US20130142418A1
公开(公告)日：2013-06-06
申请号：US13312558
申请日：2011-12-06
申请人： Roelof van Zwol , Lluis Garcia Pueyo
发明人： Roelof van Zwol , Lluis Garcia Pueyo
IPC分类号： G06K9/62
CPC分类号： G06K9/00751
摘要： Techniques are described herein for selecting representative images for video items using a trained machine learning engine. A training set is fed to a machine learning engine. The training set includes, for each image in the training set, input parameter values and an externally-generated score. Once a machine learning model has been generated based on the training set, input parameters for unscored images are fed to the trained machine learning engine. Based on the machine learning model, the trained machine learning engine generates scores for the images. To select a representative image for a particular video item, candidate images for that particular video item may be ranked based on their scores, and the candidate image with the top score may be selected as the representative image for the video item.
摘要翻译：本文描述了使用训练有素的机器学习引擎来选择用于视频项目的代表性图像的技术。训练组被馈送到机器学习引擎。对于培训集中的每个图像，训练集包括输入参数值和外部生成的分数。一旦基于训练集产生了机器学习模型，则将未分级图像的输入参数馈送到经过训练的机器学习引擎。基于机器学习模型，训练有素的机器学习引擎为图像生成分数。为了选择特定视频项目的代表性图像，可以基于它们的分数对该特定视频项目的候选图像进行排名，并且可以选择具有最高分数的候选图像作为视频项目的代表图像。

48. 发明授权

US08386935B2 Content summary and segment creation 有权
标题翻译：内容摘要和段创建
公开(公告)号：US08386935B2
公开(公告)日：2013-02-26
申请号：US12436551
申请日：2009-05-06
申请人： Roelof van Zwol , Chris Theodore Kalaboukis , Lluis Garcia Pueyo , Georgina Ramirez Camps
发明人： Roelof van Zwol , Chris Theodore Kalaboukis , Lluis Garcia Pueyo , Georgina Ramirez Camps
IPC分类号： G06F3/00
CPC分类号： G06F3/04817
摘要： Disclosed herein is an ability to create segments of content, such as video, audio, multimedia, image, animation, interactive, etc. content, to associate metadata to each segment created, and to generate a summary of content comprising one or more segments using the metadata associated with the content segments. One or more acticons represented as icons in a user interface displayable to a user can be used to indicate a starting and/or ending point for a content segment. An acticon can represent an occurrence in the content, or a reaction of a user experiencing the content, for example.
摘要翻译：本文公开的是创建内容片段的能力，例如视频，音频，多媒体，图像，动画，交互式等内容，以将元数据与创建的每个片段相关联，并且生成包含一个或多个片段的内容的概要与内容段相关联的元数据。在用户界面中表示为图标的一个或多个动作可被用于向用户显示内容片段的起始点和/或终点。例如，acticon可以表示内容中的发生，或者体验内容的用户的反应。

49. 发明申请

US20120263385A1 LOGO OR IMAGE RECOGNITION 有权
标题翻译： LOGO或图像识别
公开(公告)号：US20120263385A1
公开(公告)日：2012-10-18
申请号：US13088305
申请日：2011-04-15
申请人： Roelof van Zwol , Luis Garcia Pueyo , Stefan Romberg
发明人： Roelof van Zwol , Luis Garcia Pueyo , Stefan Romberg
IPC分类号： G06K9/64 , G06K9/46
CPC分类号： G06K9/6202 , G06K9/6211
摘要： Subject matter disclosed herein relates to electronic image object or logo recognition.
摘要翻译：本文公开的主题涉及电子图像对象或标识识别。

50. 发明申请

US20120030711A1 METHOD OR SYSTEM TO PREDICT MEDIA CONTENT PREFERENCES 有权
标题翻译：方法或系统预测媒体内容优先
公开(公告)号：US20120030711A1
公开(公告)日：2012-02-02
申请号：US12845684
申请日：2010-07-28
申请人： Adam Rae , Lluis Garcia Pueyo , Roelof van Zwol
发明人： Adam Rae , Lluis Garcia Pueyo , Roelof van Zwol
IPC分类号： H04N5/445
CPC分类号： H04N21/466 , G06F17/30268 , G06F17/30274 , H04N21/4532 , H04N21/482
摘要： Briefly, embodiments of a method or system of predicting media content preferences are disclosed.
摘要翻译：简而言之，公开了预测媒体内容偏好的方法或系统的实施例。

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