专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

91. 发明授权

US07127120B2 Systems and methods for automatically editing a video 有权
标题翻译：自动编辑视频的系统和方法
公开(公告)号：US07127120B2
公开(公告)日：2006-10-24
申请号：US10286348
申请日：2002-11-01
申请人： Xian-Sheng Hua , Lie Lu , Yu-Fei Ma , Mingjing Li , Hong-Jiang Zhang
发明人： Xian-Sheng Hua , Lie Lu , Yu-Fei Ma , Mingjing Li , Hong-Jiang Zhang
IPC分类号： G06K9/40
CPC分类号： G11B27/034 , G11B27/28
摘要： Systems and methods to automatically edit a video to generate a video summary are described. In one aspect, sub-shots are extracted from the video. Importance measures are calculated for at least a portion of the extracted sub-shots. Respective relative distributions for sub-shots having relatively higher importance measures as compared to importance measures of other sub-shots are determined. Based on the determined relative distributions, sub-shots that do not exhibit a uniform distribution with respect to other sub-shots in the particular ones are dropped. The remaining sub-shots are connected with respective transitions to generate the video summary.
摘要翻译：描述了自动编辑视频以生成视频摘要的系统和方法。在一方面，从视频中提取子拍摄。对于提取的子拍摄的至少一部分计算重要性度量。确定与其他子拍摄重要度量相比具有相对较高重要度量的子投影的相对相对分布。基于所确定的相对分布，相对于特定的其他子投影，不显示均匀分布的子投影。剩余的子拍摄与各自的转换相连接以产生视频摘要。

92. 发明授权

US09271035B2 Detecting key roles and their relationships from video 有权
标题翻译：从视频中检测关键角色及其关系
公开(公告)号：US09271035B2
公开(公告)日：2016-02-23
申请号：US13085288
申请日：2011-04-12
申请人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Yan Wang
发明人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Yan Wang
IPC分类号： H04N21/44 , G06Q30/02 , H04N21/84 , G06K9/00
CPC分类号： H04N21/44008 , G06F17/30793 , G06F17/30843 , G06K9/00718 , G06Q30/0276 , H04N21/84
摘要： Tools and techniques for acquiring key roles and their relationships from a video independent of metadata, such as cast lists and scripts, are described herein. These techniques include discovering key roles and their relationships by treating a video (e.g., a movie, television program, music video, and personal video, etc.) as a community. For instance, a video is segmented into a hierarchical structure that includes levels for scenes, shots, and key frames. In some implementations, the techniques include performing face detection and grouping on the detected key frames. In some implementations, the techniques include exploiting the key roles and their correlations in this video to discover a community. The discovered community provides for a wide variety of applications, including the automatic generation of visual summaries or video posters including acquired key roles.
摘要翻译：本文描述了从独立于元数据的视频（如演员列表和脚本）获取关键角色及其关系的工具和技术。这些技术包括通过将视频（例如，电影，电视节目，音乐视频和个人视频等）视为社区来发现关键角色及其关系。例如，视频被分割成层次结构，其包括场景，镜头和关键帧的级别。在一些实现中，这些技术包括在检测到的关键帧上执行面部检测和分组。在一些实现中，这些技术包括利用该视频中的关键角色及其相关性来发现社区。被发现的社区提供了广泛的应用，包括自动生成视觉摘要或视频海报，包括已获得的关键角色。

93. 发明授权

US09092673B2 Computing visual and textual summaries for tagged image collections 有权
标题翻译：为标记的图像集合计算视觉和文本摘要
公开(公告)号：US09092673B2
公开(公告)日：2015-07-28
申请号：US12436783
申请日：2009-05-07
申请人： Jingdong Wang , Xian-Sheng Hua , Shipeng Li , Hao Xu
发明人： Jingdong Wang , Xian-Sheng Hua , Shipeng Li , Hao Xu
IPC分类号： G06K9/62 , G06K9/00 , G06F17/30
CPC分类号： G06K9/00664 , G06F17/30265 , G06F17/30719 , G06K9/6255
摘要： Described is a technology for computing visual and textual summaries for tagged image collections. Heterogeneous affinity propagation is used to together identify both visual and textual exemplars. The heterogeneous affinity propagation finds the exemplars for relational heterogeneous data (e.g., images and words) by considering the relationships (e.g., similarities) within pairs of images, pairs of words, and relationships of words to images (affinity) in an integrated manner.
摘要翻译：描述了一种用于计算标记图像集合的视觉和文本摘要的技术。非均匀亲和度传播用于一起识别视觉和文本样本。通过考虑图像成对，单词之间的关系（例如，相似度）和单词与图像的关系（亲和性）以集成的方式，异构亲和度传播找到关系异构数据（例如，图像和单词）的示例。

94. 发明授权

US08655889B2 Autonomous mobile blogging 有权
标题翻译：自主移动博客
公开(公告)号：US08655889B2
公开(公告)日：2014-02-18
申请号：US12965604
申请日：2010-12-10
申请人： Xian-Sheng Hua , Hongzhi Li , Shipeng Li
发明人： Xian-Sheng Hua , Hongzhi Li , Shipeng Li
IPC分类号： G06F7/00 , G06F17/30
CPC分类号： G06F17/3087
摘要： An autonomous blog engine is implemented to enable the autonomous generation of a blog. The autonomous blog engine receives media objects that are captured by an electronic device during a trip session. The autonomous blog engine determines a place of interest based on photographs selected from the media objects. The autonomous blog engine then generates textual content using one or more pre-stored knowledge items that include information on the place of interest. The autonomous blog engine further autonomously publishes a blog entry on the place of interest that includes one or more photographs from the photograph cluster and the textual content.
摘要翻译：实现一个自主的博客引擎来实现自动生成博客。自主博客引擎在跳闸会话期间接收由电子设备捕获的媒体对象。自主博客引擎基于从媒体对象中选择的照片来确定兴趣点。然后，自主博客引擎使用包含感兴趣的地方的信息的一个或多个预先存储的知识项生成文本内容。自主博客引擎进一步自主地在感兴趣的地方发布一个博客条目，其中包括来自照片集群的一个或多个照片和文本内容。

95. 发明授权

US08645380B2 Optimized KD-tree for scalable search 有权
标题翻译：用于可扩展搜索的优化KD树
公开(公告)号：US08645380B2
公开(公告)日：2014-02-04
申请号：US12940880
申请日：2010-11-05
申请人： Jingdong Wang , Xian-Sheng Hua , Shipeng Li , You Jia
发明人： Jingdong Wang , Xian-Sheng Hua , Shipeng Li , You Jia
IPC分类号： G06F17/30
CPC分类号： G06F17/3028 , G06F17/30333
摘要： Techniques for constructing an optimized kd-tree are described. In an implementation, an optimized kd-tree process receives input of a set of data points applicable for large-scale computer vision applications. The process divides the set of the data points into subsets of data points with nodes while generating hyperplanes (e.g., coordinate axes). The process identifies a partition axis for each node based on the coordinate axes combined in a binary way. The optimized kd-tree process creates an optimized kd-tree that organizes the data points based on the identified partition axis. The organization of the data points in the optimized kd-tree provides efficient indexing and searching for a nearest neighbor.
摘要翻译：描述了构建优化的kd-tree的技术。在一个实现中，优化的kd-tree过程接收适用于大规模计算机视觉应用的一组数据点的输入。该过程在产生超平面（例如，坐标轴）的同时将数据点的集合划分成具有节点的数据点的子集。该过程基于以二进制方式组合的坐标轴来识别每个节点的分区轴。优化的kd-tree过程创建一个优化的kd-tree，它根据识别的分区轴组织数据点。优化的kd-tree中数据点的组织为最近邻居提供了有效的索引和搜索。

96. 发明授权

US08406573B2 Interactively ranking image search results using color layout relevance 有权
标题翻译：使用颜色布局相关性对图像搜索结果进行交互排序
公开(公告)号：US08406573B2
公开(公告)日：2013-03-26
申请号：US12341953
申请日：2008-12-22
申请人： Jingdong Wang , Shipeng Li , Xian-Sheng Hua , Yinghai Zhao
发明人： Jingdong Wang , Shipeng Li , Xian-Sheng Hua , Yinghai Zhao
IPC分类号： G06K9/60
CPC分类号： G06K9/00624 , G06F17/3025
摘要： This disclosure describes various exemplary user interfaces, methods, and computer program products for the interactively ranking image search results refinement method using a color layout. The method includes receiving a text query for an image search, presenting image search results in a structured presentation based on the text query and information from an interest color layout. The process creates image search results that may be selected by the user based on color selection palettes or color layout specification schemes. Then the process ranks the image search results by sorting the results according to similarity scores between color layouts from the image search results and the interest color layout from a user based on the color selection palettes and the color layout specification schemes.
摘要翻译：本公开描述了使用颜色布局的用于交互式排序的图像搜索结果细化方法的各种示例性用户界面，方法和计算机程序产品。该方法包括接收用于图像搜索的文本查询，基于文本查询和来自兴趣颜色布局的信息在结构化表示中呈现图像搜索结果。该过程创建可以由用户基于颜色选择调色板或颜色布局规范方案来选择的图像搜索结果。然后，该过程通过根据来自图像搜索结果的颜色布局与基于颜色选择调色板和颜色布局规范方案的用户的兴趣颜色布局之间的相似性分数来排序结果来排序图像搜索结果。

97. 发明申请

US20120297038A1 Recommendations for Social Network Based on Low-Rank Matrix Recovery 审中-公开
标题翻译：基于低阶矩阵恢复的社会网络建议
公开(公告)号：US20120297038A1
公开(公告)日：2012-11-22
申请号：US13108843
申请日：2011-05-16
申请人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Jinfeng Zhuang
发明人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Jinfeng Zhuang
IPC分类号： G06F15/173 , G06F17/30
CPC分类号： G06Q50/01
摘要： Techniques describe analyzing users and groups of a social network to identify user interests and providing recommendations for a user based on the user's identified interests. A content-awareness application obtains a collection of images and tags associated with the images belonging to members in the social network. The content-awareness application decomposes the members into a representative matrix to identify users and groups in order to calculate a similarity matrix between the users and their images based on a visual content of the images and a textual content of the tags. The content-awareness application further constructs a graph Laplacian over the users and the groups to align with the representative matrix based at least in part on the similarity matrix and further provides recommendations of groups for a user to join in the social network based at least in part on the graph Laplacian identifying the user's interests.
摘要翻译：技术描述了分析社交网络的用户和组以识别用户兴趣并基于用户识别的兴趣为用户提供建议。内容感知应用程序获得与属于社交网络中的成员的图像相关联的图像和标签的集合。内容感知应用程序将成员分解为代表性矩阵以识别用户和组，以便基于图像的可视内容和标签的文本内容来计算用户和他们的图像之间的相似性矩阵。该内容感知应用进一步构建一个关于用户和组的拉普拉斯算子，以至少部分地基于相似性矩阵与代表性矩阵一致，并进一步提供用户群体的建议，以便用户至少在拉普拉斯确定用户兴趣的一部分。

98. 发明申请

US20120263433A1 Detecting Key Roles and Their Relationships from Video 有权
标题翻译：从视频中检测关键角色及其关系
公开(公告)号：US20120263433A1
公开(公告)日：2012-10-18
申请号：US13085288
申请日：2011-04-12
申请人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Yan Wang
发明人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Yan Wang
IPC分类号： H04N9/80
CPC分类号： H04N21/44008 , G06F17/30793 , G06F17/30843 , G06K9/00718 , G06Q30/0276 , H04N21/84
摘要： Tools and techniques for acquiring key roles and their relationships from a video independent of metadata, such as cast lists and scripts, are described herein. These techniques include discovering key roles and their relationships by treating a video (e.g., a movie, television program, music video, and personal video, etc.) as a community. For instance, a video is segmented into a hierarchical structure that includes levels for scenes, shots, and key frames. In some implementations, the techniques include performing face detection and grouping on the detected key frames. In some implementations, the techniques include exploiting the key roles and their correlations in this video to discover a community. The discovered community provides for a wide variety of applications, including the automatic generation of visual summaries or video posters including acquired key roles.
摘要翻译：本文描述了从独立于元数据的视频（如演员列表和脚本）获取关键角色及其关系的工具和技术。这些技术包括通过将视频（例如，电影，电视节目，音乐视频和个人视频等）视为社区来发现关键角色及其关系。例如，视频被分割成层次结构，其包括场景，镜头和关键帧的级别。在一些实现中，这些技术包括在检测到的关键帧上执行面部检测和分组。在一些实现中，这些技术包括利用该视频中的关键角色及其相关性来发现社区。被发现的社区提供了广泛的应用，包括自动生成视觉摘要或视频海报，包括已获得的关键角色。

99. 发明申请

US20120251011A1 Event Determination From Photos 有权
标题翻译：事件确定从照片
公开(公告)号：US20120251011A1
公开(公告)日：2012-10-04
申请号：US13079592
申请日：2011-04-04
申请人： Mingyan Gao , Xian-Sheng Hua
发明人： Mingyan Gao , Xian-Sheng Hua
IPC分类号： G06K9/62
CPC分类号： G06F17/30265 , G06K9/00671
摘要： Events may be determined based on an image and context data associated with the image. An event type associated with the image may be determined based on a concept of the image. A list of events may be retrieved from an event database based on the context data. The retrieved list of events may then be ranked based on the determined event type and the context data. Through this event determination, a user may obtain information of one or more events happening at a specific location simply by capturing an image of that specific location, thereby saving the user from searching and browsing the Internet or brochure to locate the information of the one or more events at the specific location.
摘要翻译：可以基于与图像相关联的图像和上下文数据来确定事件。可以基于图像的概念来确定与图像相关联的事件类型。可以基于上下文数据从事件数据库检索事件列表。然后可以基于所确定的事件类型和上下文数据对所检索的事件列表进行排名。通过该事件确定，用户可以通过捕获特定位置的图像来获取在特定位置发生的一个或多个事件的信息，从而保存用户搜索和浏览因特网或小册子，以定位该信息的一个或多个更多的事件在特定的位置。

100. 发明授权

US08249366B2 Multi-label multi-instance learning for image classification 有权
标题翻译：用于图像分类的多标签多实例学习
公开(公告)号：US08249366B2
公开(公告)日：2012-08-21
申请号：US12140247
申请日：2008-06-16
申请人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Zheng-Jun Zha
发明人： Tao Mei , Xian-Sheng Hua , Shipeng Li , Zheng-Jun Zha
IPC分类号： G06K9/00
CPC分类号： G06K9/4638 , G06K9/342
摘要： Described is a technology by which an image is classified (e.g., grouped and/or labeled), based on multi-label multi-instance data learning-based classification according to semantic labels and regions. An image is processed in an integrated framework into multi-label multi-instance data, including region and image labels. The framework determines local association data based on each region of an image. Other multi-label multi-instance data is based on relationships between region labels of the image, relationships between image labels of the image, and relationships between the region and image labels. These data are combined to classify the image. Training is also described.
摘要翻译：基于根据语义标签和区域的基于多标签多实例数据学习的分类，描述了图像被分类（例如，分组和/或标记）的技术。图像在集成框架中被处理成多标签多实例数据，包括区域和图像标签。该框架基于图像的每个区域确定局部关联数据。其他多标签多实例数据基于图像的区域标签之间的关系，图像的图像标签之间的关系以及区域和图像标签之间的关系。组合这些数据以对图像进行分类。培训也被描述。

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