MULTI-VIDEO SYNTHESIS
    71.
    发明申请
    MULTI-VIDEO SYNTHESIS 有权
    多视频合成

    公开(公告)号:US20100149419A1

    公开(公告)日:2010-06-17

    申请号:US12334231

    申请日:2008-12-12

    IPC分类号: H04N9/74

    CPC分类号: G11B27/036

    摘要: Embodiments that provide multi-video synthesis are disclosed. In accordance with one embodiment, multi-video synthesis includes breaking a main video into a plurality of main frames and break a supplementary video into a plurality of supplementary frames. The multi-video synthesis also includes assigning one or more supplementary frames into each of a plurality of states of a Hidden Markov Model (HMM), where each of the plurality of states corresponding to one or more main frames. The multi-video synthesis further includes determining optimal frames in the plurality of main frames for insertion of the plurality of supplementary frames based on the plurality of states and visual properties. The optimal frames include optimal insertion positions. The multi-video synthesis additionally includes inserting the plurality of supplementary frames into the optimal insertion positions to form a synthesized video.

    摘要翻译: 公开了提供多视频合成的实施例。 根据一个实施例,多视频合成包括将主视频分解成多个主帧并将辅助视频分解成多个补充帧。 多视频合成还包括将一个或多个补充帧分配给隐马尔可夫模型(HMM)的多个状态中的每个状态,其中多个状态中的每一个对应于一个或多个主帧。 多视频合成还包括基于多个状态和视觉属性来确定多个主帧中的最佳帧以插入多个补充帧。 最佳帧包括最佳插入位置。 多视频合成还包括将多个辅助帧插入最佳插入位置以形成合成视频。

    Transductive Multi-Label Learning For Video Concept Detection
    72.
    发明申请
    Transductive Multi-Label Learning For Video Concept Detection 有权
    用于视频概念检测的转换多标签学习

    公开(公告)号:US20100142803A1

    公开(公告)日:2010-06-10

    申请号:US12329293

    申请日:2008-12-05

    IPC分类号: G06K9/62

    CPC分类号: G06K9/00718 G06K9/6297

    摘要: This disclosure describes various exemplary method and computer program products for transductive multi-label classification in detecting video concepts for information retrieval. This disclosure describes utilizing a hidden Markov random field formulation to detect labels for concepts in a video content and modeling a multi-label interdependence between the labels by a pairwise Markov random field. The process groups the labels into several parts to speed up a labeling inference and calculates a conditional probability score for the labels, the conditional probability scores are ordered for ranking in a video retrieval evaluation.

    摘要翻译: 本公开描述了用于检测用于信息检索的视频概念的用于转换多标签分类的各种示例性方法和计算机程序产品。 本公开描述了利用隐马尔科夫随机场公式来检测视频内容中的概念的标签,并通过成对的马尔可夫随机场对标签之间的多标签相互依赖进行建模。 该过程将标签分组成几个部分,以加快标签推理,并计算标签的条件概率分数,条件概率分数被排序用于视频检索评估中的排名。

    Multi-Label Active Learning
    73.
    发明申请
    Multi-Label Active Learning 有权
    多标签主动学习

    公开(公告)号:US20090125461A1

    公开(公告)日:2009-05-14

    申请号:US11958050

    申请日:2007-12-17

    IPC分类号: G06F15/18

    CPC分类号: G06N99/005

    摘要: Multi-label active learning may entail training a classifier with a set of training samples having multiple labels per sample. In an example embodiment, a method includes accepting a set of training samples, with the set of training samples having multiple respective samples that are each respectively associated with multiple labels. The set of training samples is analyzed to select a sample-label pair responsive to at least one error parameter. The selected sample-label pair is then submitted to an oracle for labeling.

    摘要翻译: 多标签主动学习可能需要对分类器训练一组具有每个样本的多个标签的训练样本。 在示例实施例中,一种方法包括接受一组训练样本,其中该组训练样本具有多个相应样本,每个样本分别与多个标签相关联。 分析该组训练样本以响应于至少一个误差参数来选择样本标签对。 然后将选定的样品标签对提交给oracle进行标记。

    MULTI-MODAL RELEVANCY MATCHING
    74.
    发明申请
    MULTI-MODAL RELEVANCY MATCHING 审中-公开
    多模式相关匹配

    公开(公告)号:US20090076882A1

    公开(公告)日:2009-03-19

    申请号:US11855872

    申请日:2007-09-14

    CPC分类号: G06Q30/0242 G06Q30/02

    摘要: This document describes techniques capable of associating relevant entities, such as advertisements, with insertion points within a media file. These techniques calculate a global relevancy between entities and the media file. These techniques may also calculate a local relevancy between the entities and one or more insertion points within the media file. Both global and local relevancies may employ textual and non-textual information. With use of the calculated global and local relevancies, the techniques associate one or more entities with each of the one or more insertion points in the media file. These techniques thus enable, for each insertion point, associating a most relevant entity for a particular insertion point with the insertion point. Therefore, when a user consumes the media file the user may also consume a most relevant entity at and for each insertion point in the media file.

    摘要翻译: 本文档描述了能够将相关实体(例如广告)与媒体文件中的插入点相关联的技术。 这些技术计算实体和媒体文件之间的全局相关性。 这些技术还可以计算实体与媒体文件中的一个或多个插入点之间的局部相关性。 全球和本地的相关机构都可以使用文本和非文本信息。 使用计算的全局和本地相关性,这些技术将一个或多个实体与媒体文件中的一个或多个插入点中的每一个相关联。 因此,对于每个插入点,这些技术使得将特定插入点的最相关实体与插入点相关联。 因此,当用户消费媒体文件时,用户也可以在媒体文件中的每一个插入点处和消费最相关的实体。

    Template-based multimedia capturing
    75.
    发明申请
    Template-based multimedia capturing 有权
    基于模板的多媒体捕获

    公开(公告)号:US20070101267A1

    公开(公告)日:2007-05-03

    申请号:US11263709

    申请日:2005-11-01

    IPC分类号: G06K9/54

    CPC分类号: G06F17/30244

    摘要: Systems and methods for template-based multimedia capturing are described. In one aspect, a capturing template is selected to facilitate capturing a particular quantity and type(s) of media content. Media content is captured based on a temporal structure provided by the capturing template. These quantities and types of media content captured with respect to the temporal structure facilitate media content browsing, indexing, authoring, and sharing activities.

    摘要翻译: 描述了基于模板的多媒体捕获的系统和方法。 在一个方面,选择捕获模板以便于捕获特定数量和类型的媒体内容。 基于由捕获模板提供的时间结构捕获媒体内容。 相对于时间结构捕获的这些数量和类型的媒体内容便于媒体内容浏览,索引,创作和共享活动。

    High dynamic range texture compression
    76.
    发明授权
    High dynamic range texture compression 有权
    高动态范围纹理压缩

    公开(公告)号:US08498476B2

    公开(公告)日:2013-07-30

    申请号:US13429208

    申请日:2012-03-23

    IPC分类号: G06K9/00

    CPC分类号: G06T9/00

    摘要: A method for compressing a high dynamic range (HDR) texture. A first block of texels of the HDR texture in a red-green-blue (RGB) space may be transformed to a second block of texels in a luminance-chrominance space. The first block may have red values, green values and blue values. The second block may have luminance values and chrominance values. The chrominance values may be based on a sum of the red values, a sum of the green values and a sum of the blue values. The luminance values and the chrominance values may be converted to an 8-bit integer format. The luminance values may be modified to restore a local linearity property to the second block. The second block may be compressed.

    摘要翻译: 一种用于压缩高动态范围(HDR)纹理的方法。 红 - 绿 - 蓝(RGB)空间中的HDR纹理的纹素的第一块可以被变换为亮度 - 色度空间中的第二纹理纹理块。 第一个块可能具有红色值,绿色值和蓝色值。 第二块可以具有亮度值和色度值。 色度值可以基于红色值的总和,绿色值的和与蓝色值的和。 亮度值和色度值可以被转换成8位整数格式。 可以修改亮度值以恢复与第二块的局部线性特性。 第二个块可能被压缩。

    Video coding using spatio-temporal texture synthesis
    77.
    发明授权
    Video coding using spatio-temporal texture synthesis 有权
    视频编码采用时空纹理合成

    公开(公告)号:US08208556B2

    公开(公告)日:2012-06-26

    申请号:US11768862

    申请日:2007-06-26

    IPC分类号: H04N11/04

    摘要: Systems and methods for video coding using spatio-temporal texture synthesis are described. In one aspect, a video data coding pipeline portion of the codec removes texture blocks from the video data to generate coded video data. The removed texture blocks are selected based on an objective determination that each of the remove texture blocks can be synthesized from spatio-temporal neighboring samples during decoding operations. The objective determinations are made using local block-based motion information independent of global motion models. An indication of which texture blocks were removed is provided to a decoder in addition to the coded video data. Decoding logic of the codec decodes the video data using a standard decoding algorithm. The decoding logic also restores the removed texture blocks via spatio-temporal texture synthesis to generate synthesized video data. The decoded and synthesized video data is presented to a user.

    摘要翻译: 描述使用时空纹理合成的视频编码的系统和方法。 一方面,编解码器的视频数据编码流水线部分从视频数据中去除纹理块以产生编码视频数据。 基于在解码操作期间可以从空时相邻采样中合成每个去除纹理块的目标确定来选择去除的纹理块。 使用与全局运动模型无关的局部基于块的运动信息进行客观确定。 去除了纹理块的指示除了编码的视频数据之外还提供给解码器。 编解码器的解码逻辑使用标准解码算法解码视频数据。 解码逻辑还通过空间 - 时间纹理合成恢复去除的纹理块,以产生合成的视频数据。 解码和合成的视频数据被呈现给用户。

    Enhancement layer switching for scalable video coding
    78.
    发明授权
    Enhancement layer switching for scalable video coding 有权
    用于可扩展视频编码的增强层交换

    公开(公告)号:US08130830B2

    公开(公告)日:2012-03-06

    申请号:US12112821

    申请日:2008-04-30

    IPC分类号: H04N7/12 H04N11/02

    摘要: An exemplary system includes a data encoder generating a base layer bitstream encoded at a base bit-rate, and a plurality of enhancement layer bitstreams encoded at different enhancement layer bit-rates, and a bitstream selection module selecting one of the enhancement layer bitstreams every video frame based on available channel bandwidth. A method includes transmitting a first enhancement layer bitstream encoded at a first bit-rate, detecting a transition in network bandwidth through a switching bit-rate, and transmitting a second enhancement layer bitstream encoded at a second bit-rate based on the transition in network bandwidth.

    摘要翻译: 一个示例性系统包括产生以基本比特率编码的基本层比特流的数据编码器和以不同增强层比特率编码的多个增强层比特流,以及比特流选择模块,每个视频选择增强层比特流之一 基于可用信道带宽的帧。 一种方法包括发送以第一比特率编码的第一增强层比特流,通过切换比特率检测网络带宽中的转换,以及基于网络中的转换来发送以第二比特率编码的第二增强层比特流 带宽。

    RESIZING OF DIGITAL IMAGES
    79.
    发明申请
    RESIZING OF DIGITAL IMAGES 有权
    数字图像的调整

    公开(公告)号:US20110170801A1

    公开(公告)日:2011-07-14

    申请号:US12684925

    申请日:2010-01-09

    IPC分类号: G06K9/32

    摘要: Digital images are resized according to a prescribed image scaling factor. An original image is re-sampled according to the scaling factor, resulting in an initial resized image. A probability of text (POT) map is generated for the initial resized image, where the POT map specifies a smoothed POT value for each pixel in the initial resized image. A weighting factor (WF) map is generated which maps each different smoothed POT value to a particular WF value. The WF map is used to calculate an adjusted luminance value for each pixel in the initial resized image, resulting in a final resized image.

    摘要翻译: 数字图像根据规定的图像缩放因子调整大小。 根据缩放因子重新采样原始图像,导致初始调整大小的图像。 为初始调整大小的图像生成文本(POT)图的概率,其中POT映射指定初始调整大小的图像中每个像素的平滑POT值。 生成加权因子(WF)图,其将每个不同的平滑POT值映射到特定的WF值。 WF图用于计算初始调整大小的图像中每个像素的调整亮度值,得到最终调整大小的图像。

    Textual image coding
    80.
    发明授权
    Textual image coding 有权
    文字图像编码

    公开(公告)号:US07903873B2

    公开(公告)日:2011-03-08

    申请号:US11855075

    申请日:2007-09-13

    IPC分类号: G06K9/36

    摘要: Textual image coding involves coding textual portions of an image. In an example embodiment, a textual block of an image is decomposed into multiple base colors and an index map, with the index map having index values that each reference a base color so as to represent the textual block. A set of neighbor index values are ascertained for a particular index of the index map. A context that matches the neighbor index values is generated from among multiple contexts. The matching context includes a set of symbols. At least one symbol-to-value mapping is determined based on the matching context and a symbol to which the particular index corresponds. The particular index is remapped to a particular value in accordance with the symbol-to-value mapping and the symbol to which the particular index corresponds.

    摘要翻译: 文本图像编码涉及对图像的文本部分进行编码。 在示例实施例中,图像的文本块被分解为多个基色和索引图,索引图具有每个引用基色以便表示文本块的索引值。 确定索引图的特定索引的一组邻近索引值。 从多个上下文中生成匹配邻居索引值的上下文。 匹配的上下文包括一组符号。 基于匹配上下文和特定索引对应的符号来确定至少一个符号到值映射。 根据符号对值映射和特定索引对应的符号将特定索引重新映射到特定值。