会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 3. 发明申请
    • Automatic video editing for real-time multi-point video conferencing
    • 自动视频编辑实时多点视频会议
    • US20060251384A1
    • 2006-11-09
    • US11182565
    • 2005-07-15
    • David VronayShuo WangDingmei ZhangWeiwei Zhang
    • David VronayShuo WangDingmei ZhangWeiwei Zhang
    • H04N5/93
    • G11B27/034H04N7/147H04N7/15
    • An “automated video editor” (AVE) automatically processes one or more input videos to create an edited video stream with little or no user interaction. The AVE produces cinematic effects such as cross-cuts, zooms, pans, insets, 3-D effects, etc., by applying a combination of cinematic rules, object recognition techniques, and digital editing of the input video. Consequently, the AVE is capable of using a simple video taken with a fixed camera to automatically simulate cinematic editing effects that would normally require multiple cameras and/or professional editing. The AVE first defines a list of scenes in the video and generates a rank-ordered list of candidate shots for each scene. Each frame of each scene is then analyzed or “parsed” using object detection techniques (“detectors”) for isolating unique objects (faces, moving/stationary objects, etc.) in the scene. Shots are then automatically selected for each scene and used to construct the edited video stream.
    • “自动视频编辑器”(AVE)自动处理一个或多个输入视频,以创建一个没有或没有用户交互的编辑视频流。 通过应用电影规则,对象识别技术和输入视频的数字编辑的组合,AVE产生电影效果,如横切,缩放,平底锅,插图,3-D效果等。 因此,AVE能够使用固定相机拍摄的简单视频来自动模拟通常需要多个相机和/或专业编辑的电影编辑效果。 AVE首先定义视频中的场景列表,并为每个场景生成候选镜头的排序列表。 然后使用对象检测技术(“检测器”)分析或“解析”每个场景的每个帧,以隔离场景中的独特对象(面部,移动/静止对象等)。 然后自动为每个场景选择拍摄,并用于构建编辑过的视频流。
    • 4. 发明申请
    • Automatic video editing for real-time generation of multiplayer game show videos
    • 自动视频编辑实时生成多人游戏节目视频
    • US20060251383A1
    • 2006-11-09
    • US11182542
    • 2005-07-15
    • David VronayShuo WangDongmei ZhangWeiwei Zhang
    • David VronayShuo WangDongmei ZhangWeiwei Zhang
    • H04N5/93
    • G11B27/034H04N7/147H04N7/15
    • An “automated video editor” (AVE) automatically processes one or more input videos to create an edited video stream with little or no user interaction. The AVE produces cinematic effects such as cross-cuts, zooms, pans, insets, 3-D effects, etc., by applying a combination of cinematic rules, object recognition techniques, and digital editing of the input video. Consequently, the AVE is capable of using a simple video taken with a fixed camera to automatically simulate cinematic editing effects that would normally require multiple cameras and/or professional editing. The AVE first defines a list of scenes in the video and generates a rank-ordered list of candidate shots for each scene. Each frame of each scene is then analyzed or “parsed” using object detection techniques (“detectors”) for isolating unique objects (faces, moving/stationary objects, etc.) in the scene. Shots are then automatically selected for each scene and used to construct the edited video stream.
    • “自动视频编辑器”(AVE)自动处理一个或多个输入视频,以创建一个没有或没有用户交互的编辑视频流。 通过应用电影规则,对象识别技术和输入视频的数字编辑的组合,AVE产生电影效果,如横切,缩放,平底锅,插图,3-D效果等。 因此,AVE能够使用固定相机拍摄的简单视频来自动模拟通常需要多个相机和/或专业编辑的电影编辑效果。 AVE首先定义视频中的场景列表,并为每个场景生成候选镜头的排序列表。 然后使用对象检测技术(“检测器”)分析或“解析”每个场景的每个帧,以隔离场景中的独特对象(面部,移动/静止对象等)。 然后自动为每个场景选择拍摄,并用于构建编辑过的视频流。
    • 5. 发明授权
    • Graphical user interface system and process for navigating a set of images
    • 用于导航一组图像的图形用户界面系统和过程
    • US07737995B2
    • 2010-06-15
    • US11069806
    • 2005-02-28
    • David VronayShuo Wang
    • David VronayShuo Wang
    • G09G5/02
    • G06F17/30274
    • A system and process for navigating unstructured or loosely structured image sets on a display screen is presented. These image sets are navigated by grouping each image thereof into clusters and arranging the clusters in a left-to-right or up-and-down manner. A set number of the clusters are displayed to a viewer. The viewer can then scroll through and select another cluster in the arrangement as desired. Within a cluster, images are arranged in a grid in a sequence order based on a sequence number assigned to each in the clustering procedure. The viewer is also able to zoom into a selected cluster to, in effect, successively form smaller sub-clusters until only a single image is displayed in a cluster under consideration. In addition, the viewer can zoom out again in a similar manner.
    • 介绍了在显示屏幕上导航非结构化或松散结构化图像集的系统和过程。 这些图像集合通过将其每个图像分组成簇并且以左到右或上下方式布置簇来导航。 集合的集合数量将显示给查看器。 然后,观看者可以根据需要滚动并选择该排列中的另一个簇。 在集群中,基于分配给聚类过程中的每一个的序列号,按照序列顺序将图像排列成网格。 观看者还能够将所选择的集群放大至实际上依次形成较小的子集群,直到在所考虑的集群中仅显示单个图像。 此外,观看者可以以类似的方式再次缩小。
    • 6. 发明申请
    • System and method for automatic video editing using object recognition
    • 使用对象识别自动视频编辑的系统和方法
    • US20060251382A1
    • 2006-11-09
    • US11125384
    • 2005-05-09
    • David VronayShuo WangDongmei ZhangWeiwei Zhang
    • David VronayShuo WangDongmei ZhangWeiwei Zhang
    • H04N5/93
    • G11B27/034H04N7/147H04N7/15
    • An “automated video editor” (AVE) automatically processes one or more input videos to create an edited video stream with little or no user interaction. The AVE produces cinematic effects such as cross-cuts, zooms, pans, insets, 3-D effects, etc., by applying a combination of cinematic rules, object recognition techniques, and digital editing of the input video. Consequently, the AVE is capable of using a simple video taken with a fixed camera to automatically simulate cinematic editing effects that would normally require multiple cameras and/or professional editing. The AVE first defines a list of scenes in the video and generates a rank-ordered list of candidate shots for each scene. Each frame of each scene is then analyzed or “parsed” using object detection techniques (“detectors”) for isolating unique objects (faces, moving/stationary objects, etc.) in the scene. Shots are then automatically selected for each scene and used to construct the edited video stream.
    • “自动视频编辑器”(AVE)自动处理一个或多个输入视频,以创建一个没有或没有用户交互的编辑视频流。 通过应用电影规则,对象识别技术和输入视频的数字编辑的组合,AVE产生电影效果,如横切,缩放,平底锅,插图,3-D效果等。 因此,AVE能够使用固定相机拍摄的简单视频来自动模拟通常需要多个相机和/或专业编辑的电影编辑效果。 AVE首先定义视频中的场景列表,并为每个场景生成候选镜头的排序列表。 然后使用对象检测技术(“检测器”)分析或“解析”每个场景的每个帧,以隔离场景中的独特对象(面部,移动/静止对象等)。 然后自动为每个场景选择拍摄,并用于构建编辑过的视频流。
    • 7. 发明申请
    • Graphical user interface system and process for navigating a set of images
    • 用于导航一组图像的图形用户界面系统和过程
    • US20060193538A1
    • 2006-08-31
    • US11069806
    • 2005-02-28
    • David VronayShuo Wang
    • David VronayShuo Wang
    • G06K9/54
    • G06F17/30274
    • A system and process for navigating unstructured or loosely structured image sets on a display screen is presented. These image sets are navigated by grouping each image thereof into clusters and arranging the clusters in a left-to-right or up-and-down manner. A set number of the clusters are displayed to a viewer. The viewer can then scroll through and select another cluster in the arrangement as desired. Within a cluster, images are arranged in a grid in a sequence order based on a sequence number assigned to each in the clustering procedure. The viewer is also able to zoom into a selected cluster to, in effect, successively form smaller sub-clusters until only a single image is displayed in a cluster under consideration. In addition, the viewer can zoom out again in a similar manner.
    • 介绍了在显示屏幕上导航非结构化或松散结构化图像集的系统和过程。 这些图像集合通过将其每个图像分组成簇并且以左到右或上下方式布置簇来导航。 集合的集合数量将显示给查看器。 然后,观看者可以根据需要滚动并选择该排列中的另一个簇。 在集群中,基于分配给聚类过程中的每一个的序列号,按照序列顺序将图像排列成网格。 观看者还能够将所选择的集群放大至实际上依次形成较小的子集群,直到在所考虑的集群中仅显示单个图像。 此外,观看者可以以类似的方式再次缩小。
    • 8. 发明申请
    • STORY TEMPLATE STRUCTURES ASSOCIATED WITH STORY ENHANCING CONTENT AND RULES
    • 与故事增强内容和规则相关的故事模式结构
    • US20060253783A1
    • 2006-11-09
    • US10908376
    • 2005-05-09
    • David VronayShuo WangXiang-Sheng HuaXiao-Ming Ji
    • David VronayShuo WangXiang-Sheng HuaXiao-Ming Ji
    • G06F17/00
    • G06F17/248
    • Story events may be obtained from a media collection from which a structured story may be generated. Story template structures are provided that may include template content which may convey one or more well-known abstract meanings, such as emotions or popular media themes (e.g., movies). The story template structures may also include template rules that may ensure the story events are formatted in a manner substantially consistent with the well-known abstract meanings intended to be conveyed. The story events obtained from the media collection may be organized within the story template structures so that the template rules are applied to the events and the well-known abstract meanings are associated with the events. This ensures that the story events in the structured story may be presented in a coherent manner that conveys the desired abstract meanings for particular story events.
    • 故事事件可以从可以从中生成结构化故事的媒体集合获得。 提供故事模板结构,其可以包括可以传达一个或多个众所周知的抽象含义的模板内容,例如情绪或流行媒体主题(例如电影)。 故事模板结构还可以包括模板规则,其可以确保故事事件被格式化为与将要传达的众所周知的抽象意义基本一致的方式。 从媒体集合获得的故事可以在故事模板结构中组织,使得模板规则被应用于事件,并且众所周知的抽象含义与事件相关联。 这可以确保结构化故事中的故事可以以一致的方式呈现,以便为特定的故事事件传达所需的抽象意义。