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

US08494983B2 Object-sensitive image search 有权
标题翻译：对象敏感图像搜索
公开(公告)号：US08494983B2
公开(公告)日：2013-07-23
申请号：US12947083
申请日：2010-11-16
申请人： Meng Wang , Xian-Sheng Hua , Yan Song
发明人： Meng Wang , Xian-Sheng Hua , Yan Song
IPC分类号： G06F15/18
CPC分类号： G06F17/30256 , G06K9/6259 , G06N99/005
摘要： Methods and systems for object-sensitive image searches are described herein. These methods and systems are usable for receiving a query for an image of an object and providing a ranked list of query results to the user based on a ranking of the images. The object-sensitive image searches may generate a pre-trained multi-instance learning (MIL) model trained from free training data from users sharing images at websites to identify a common pattern of the object, and/or may generate a MIL model “on the fly” trained from pseudo-positive and pseudo-negative samples of query results to identify a common pattern of the object. As such, the user is presented with query results that include images that prominently display the object near the top of the results.
摘要翻译：本文描述了用于对象敏感图像搜索的方法和系统。这些方法和系统可用于接收对象的图像的查询，并且基于图像的排名向用户提供排序的查询结果列表。对象敏感图像搜索可以生成预先训练的来自在网站上共享图像的用户的免费训练数据训练的多实例学习（MIL）模型，以识别对象的共同模式，和/或可以生成MIL模型飞行“从查询结果的伪正和伪负样本中训练，以识别对象的共同模式。因此，向用户呈现包括在结果顶部附近显着地显示对象的图像的查询结果。

2. 发明申请

US20120123976A1 Object-Sensitive Image Search 有权
标题翻译：对象敏感图像搜索
公开(公告)号：US20120123976A1
公开(公告)日：2012-05-17
申请号：US12947083
申请日：2010-11-16
申请人： Meng Wang , Xian-Sheng Hua , Yan Song
发明人： Meng Wang , Xian-Sheng Hua , Yan Song
IPC分类号： G06F15/18 , G06F17/30
CPC分类号： G06F17/30256 , G06K9/6259 , G06N99/005
摘要： Methods and systems for object-sensitive image searches are described herein. These methods and systems are usable for receiving a query for an image of an object and providing a ranked list of query results to the user based on a ranking of the images. The object-sensitive image searches may generate a pre-trained multi-instance learning (MIL) model trained from free training data from users sharing images at websites to identify a common pattern of the object, and/or may generate a MIL model “on the fly” trained from pseudo-positive and pseudo-negative samples of query results to identify a common pattern of the object. As such, the user is presented with query results that include images that prominently display the object near the top of the results.
摘要翻译：本文描述了用于对象敏感图像搜索的方法和系统。这些方法和系统可用于接收对象的图像的查询，并且基于图像的排名向用户提供排序的查询结果列表。对象敏感图像搜索可以生成预先训练的来自在网站上共享图像的用户的免费训练数据训练的多实例学习（MIL）模型，以识别对象的共同模式，和/或可以生成MIL模型飞行“从查询结果的伪正和伪负样本中训练，以识别对象的共同模式。因此，向用户呈现包括在结果顶部附近显着地显示对象的图像的查询结果。

3. 发明授权

US09047319B2 Tag association with image regions 有权
标题翻译：标签与图像区域的关联
公开(公告)号：US09047319B2
公开(公告)日：2015-06-02
申请号：US12972203
申请日：2010-12-17
申请人： Xian-Sheng Hua , Kuiyuan Yang , Meng Wang , Hong-Jiang Zhang
发明人： Xian-Sheng Hua , Kuiyuan Yang , Meng Wang , Hong-Jiang Zhang
IPC分类号： G06F17/30 , G06K9/00
CPC分类号： G06F17/30256 , G06F17/30268
摘要： A computing device configured to determine that one or more regions of an image are associated with a tag of the image is described herein. The computing device is further configured to determine one or more attribute tags describing at least one of the content or context of the one or more regions. Upon determining the attribute tags, the computing device associates the attribute tags with the tag to enable image searching based on the tag and attribute tags.
摘要翻译：在此描述了被配置为确定图像的一个或多个区域与图像的标签相关联的计算设备。计算设备还被配置为确定描述一个或多个区域的内容或上下文中的至少一个的一个或多个属性标签。在确定属性标签之后，计算设备将属性标签与标签相关联，以便基于标签和属性标签启用图像搜索。

4. 发明申请

US20120158721A1 Tag Association with Image Regions 有权
标题翻译：标签与图像区域的关联
公开(公告)号：US20120158721A1
公开(公告)日：2012-06-21
申请号：US12972203
申请日：2010-12-17
申请人： Xian-Sheng Hua , Kuiyuan Yang , Meng Wang , Hong-Jiang Zhang
发明人： Xian-Sheng Hua , Kuiyuan Yang , Meng Wang , Hong-Jiang Zhang
IPC分类号： G06F17/30
CPC分类号： G06F17/30256 , G06F17/30268
摘要： A computing device configured to determine that one or more regions of an image are associated with a tag of the image is described herein. The computing device is further configured to determine one or more attribute tags describing at least one of the content or context of the one or more regions. Upon determining the attribute tags, the computing device associates the attribute tags with the tag to enable image searching based on the tag and attribute tags.
摘要翻译：在此描述了被配置为确定图像的一个或多个区域与图像的标签相关联的计算设备。计算设备还被配置为确定描述一个或多个区域的内容或上下文中的至少一个的一个或多个属性标签。在确定属性标签之后，计算设备将属性标签与标签相关联，以便基于标签和属性标签启用图像搜索。

5. 发明申请

US20100185624A1 COLORBLIND ACCESSIBLE IMAGE SEARCH 有权
标题翻译： COLORBLIND可访问的图像搜索
公开(公告)号：US20100185624A1
公开(公告)日：2010-07-22
申请号：US12355795
申请日：2009-01-18
申请人： Meng Wang , Linjun Yang , Xian-Sheng Hua
发明人： Meng Wang , Linjun Yang , Xian-Sheng Hua
IPC分类号： G06F17/30
CPC分类号： G06F17/3025
摘要： Colorblind accessible image search technique embodiments are presented that re-rank the results of a relevance-ranked image search to account for the accessibility of the images to a colorblind person. This is accomplished by first computing a colorblind accessibility quantity for each image of interest in the search results. A colorblind accessibility quantity quantizes the degree to which color information is preserved when an image is perceived by a colorblind person viewing the image. It is computed by generating a colorblind version of an image that simulates how the image would appear to the colorblind person. An amount quantifying the loss of color information between the image and the colorblind version of the image is then estimated. This estimate is used to compute the colorblind accessibility quantity for the image. Once the colorblind accessibility quantities have been computed, the image search results are re-ranked based on these quantities.
摘要翻译：呈现了彩色盲可访问图像搜索技术实施例，其对排序相关的图像搜索的结果进行重新排序，以便将图像的可访问性应用于彩色盲人。这是通过首先计算搜索结果中感兴趣的每个图像的色盲辅助数量来实现的。彩色可见量可以量化当查看图像的彩色盲人感知到图像时保留颜色信息的程度。它通过生成图像的彩色版本来计算，该图像模拟图像将如何显示给彩色盲人。然后估计量化图像和图像的彩色版本之间的颜色信息的损失的量。该估计用于计算图像的色盲辅助数量。一旦计算了色盲辅助数量，就会根据这些数量重新排列图像搜索结果。

6. 发明授权

US08682065B2 Distance metric learning with feature decomposition 有权
标题翻译：距离度量学习与特征分解
公开(公告)号：US08682065B2
公开(公告)日：2014-03-25
申请号：US12344018
申请日：2008-12-24
申请人： Meng Wang , Xian-Sheng Hua
发明人： Meng Wang , Xian-Sheng Hua
IPC分类号： G06K9/00
CPC分类号： G06K9/6235 , G06K9/6215
摘要： This disclosure describes various exemplary systems, computer program products, and methods for feature distance metric learning with feature decomposition (DMLFD). The disclosure describes decomposing a high-dimensional feature space into one or more low-dimensional feature spaces according to minimum dependence. Furthermore, the disclosure describes how the sub-metrics are constructed and combined to form a global metric.
摘要翻译：本公开描述了具有特征分解（DMLFD）的各种示例性系统，计算机程序产品和用于特征距离度量学习的方法。本公开描述了根据最小依赖性将高维特征空间分解为一个或多个低维特征空间。此外，本公开描述如何构建和组合子度量以形成全局度量。

7. 发明授权

US08526724B2 In-image accessibility indication 有权
标题翻译：图像内可访问性指示
公开(公告)号：US08526724B2
公开(公告)日：2013-09-03
申请号：US12948519
申请日：2010-11-17
申请人： Meng Wang , Yelong Sheng , Xian-Sheng Hua
发明人： Meng Wang , Yelong Sheng , Xian-Sheng Hua
IPC分类号： G06K9/00
CPC分类号： G06K9/036 , G06T7/0002 , G06T7/11 , G06T2207/30168
摘要： Methods and systems for in-image accessibility indication are described herein. These methods and systems are usable to receive an image being designed, locate colorblind inaccessible regions of the image based on located colorblind inaccessible points, and indicate the located colorblind inaccessible regions in the image to a designer while the designer is creating the image. As such, the designer is able to quickly identify regions of the designed image that may be difficult for colorblind viewers to see and, with this information, the designer is able to modify the image accordingly.
摘要翻译：本文描述了用于图像内可访问性指示的方法和系统。这些方法和系统可用于接收正在设计的图像，基于所定位的色盲不可访问点来定位彩色盲图像的不可访问区域，并且在设计者创建图像时将图像中定位的彩色盲区不可访问区域指示给设计者。因此，设计者能够快速识别设计图像的区域，这对于彩色盲人观看者来说可能是困难的，并且通过该信息，设计者能够相应地修改图像。

8. 发明申请

US20120143797A1 Metric-Label Co-Learning 审中-公开
标题翻译：公制标签共同学习
公开(公告)号：US20120143797A1
公开(公告)日：2012-06-07
申请号：US12961124
申请日：2010-12-06
申请人： Meng Wang , Xian-Sheng Hua , Bo Liu
发明人： Meng Wang , Xian-Sheng Hua , Bo Liu
IPC分类号： G06F15/18 , G06N5/02
CPC分类号： G06N20/00
摘要： Labels for unlabeled media samples may be determined automatically. Characteristics and/or features of an unlabeled media sample are detected and used to iteratively optimize a distance metric and one or more labels for the unlabeled media sample according to an algorithm. The labels may be used to produce training data for a machine learning process.
摘要翻译：可以自动确定未标记的介质样品的标签。检测未标记的媒体样本的特征和/或特征，并用于根据算法对未标记的媒体样本的距离度量和一个或多个标签进行迭代优化。这些标签可用于产生用于机器学习过程的训练数据。

9. 发明申请

US20100250190A1 TAG RANKING 有权
标题翻译： TAG排名
公开(公告)号：US20100250190A1
公开(公告)日：2010-09-30
申请号：US12415722
申请日：2009-03-31
申请人： HongJiang Zhang , Dong Liu , Meng Wang , Linjun Yang , Xian-Sheng Hua
发明人： HongJiang Zhang , Dong Liu , Meng Wang , Linjun Yang , Xian-Sheng Hua
IPC分类号： G06F17/18
CPC分类号： G06F17/30038
摘要： Technologies for generating a boosted tag ranking for a media instance, the boosted tag ranking based on probabilistic relevance estimation and tag correlation refining. Such boosted tag rankings may be used for search result ranking, tag recommendation, and group recommendation.
摘要翻译：用于生成媒体实例的增强标签排名的技术，基于概率相关性估计和标签相关性提炼的提升标签排名。这种提升的标签排名可以用于搜索结果排名，标签推荐和组推荐。

10. 发明申请

US20100205202A1 Visual and Textual Query Suggestion 有权
标题翻译：视觉和文本查询建议
公开(公告)号：US20100205202A1
公开(公告)日：2010-08-12
申请号：US12369421
申请日：2009-02-11
申请人： Linjun Yang , Meng Wang , Zhengjun Zha , Tao Mei , Xian-Sheng Hua
发明人： Linjun Yang , Meng Wang , Zhengjun Zha , Tao Mei , Xian-Sheng Hua
IPC分类号： G06F17/30
CPC分类号： G06F17/3064 , G06F17/30277 , G06F17/30864
摘要： Techniques described herein enable better understanding of the intent of a user that submits a particular search query. These techniques receive a search request for images associated with a particular query. In response, the techniques determine images that are associated with the query, as well as other keywords that are associated with these images. The techniques then cluster, for each set of images associated with one of these keywords, the set of images into multiple groups. The techniques then rank the images and determine a representative image of each cluster. Finally, the tools suggest, to the user that submitted the query, to refine the search based on user selection of a keyword and a representative image. Thus, the techniques better understand the user's intent by allowing the user to refine the search based on another keyword and based on an image on which the user wishes to focus the search.
摘要翻译：本文描述的技术能够更好地理解提交特定搜索查询的用户的意图。这些技术接收与特定查询相关联的图像的搜索请求。作为响应，这些技术确定与查询相关联的图像以及与这些图像相关联的其他关键词。然后，对于与这些关键词之一相关联的每组图像，该技术将该组图像聚类成多个组。然后，技术对图像进行排序并确定每个聚类的代表图像。最后，工具向提交查询的用户建议，根据用户对关键字和代表图像的选择来优化搜索。因此，这些技术通过允许用户基于另一个关键字来改进搜索并且基于用户希望集中搜索的图像来更好地理解用户的意图。

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