知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

84 条记录 (耗时 0.028 秒)

    IMAGE GUIDED VIDEO THUMBNAIL GENERATION FOR E-COMMERCE APPLICATIONS
    2.
    发明公开
    IMAGE GUIDED VIDEO THUMBNAIL GENERATION FOR E-COMMERCE APPLICATIONS 审中-公开

    公开(公告)号：US20230177807A1

    公开(公告)日：2023-06-08

    申请号：US17545497

    申请日：2021-12-08

    申请人： eBay Inc.

    发明人： Berkan Solmaz

    IPC分类号： G06V10/74 ,  G06Q30/06 ,  G06F16/74 ,  G06F16/783 ,  G06V10/75

    CPC分类号： G06V10/761 ,  G06Q30/0633 ,  G06Q30/0641 ,  G06F16/743 ,  G06F16/7847 ,  G06V10/75

    摘要： Systems and methods are provided for automatically generating a thumbnail for a video on an online shopping site. The disclosed technology automatically generates a thumbnail for a video, where the thumbnail represents an item but not necessarily content of the video. A thumbnail generator receives a video that describes the item and an ordered list of item images associated with the item used in an item listing. The thumbnail generator extracts video frames from the video based on sampling rules and determines similarity scores for the sampled video frames. A similarity score indicates a degree of similarity between content of a video frame and an item image. The thumbnail generator determines weighted similarity scores based item images and occurrences of sampled video frames in the video. The disclosed technology generates a thumbnail for the video by selecting a sample video frame based on the weighted similarity scores.

    VIDEO PROCESSING SYSTEM, VIDEO PROCESSING METHOD, VIDEO PROCESSING APPARATUS, CONTROL METHOD OF THE APPARATUS, AND STORAGE MEDIUM STORING CONTROL PROGRAM OF THE APPARATUS
    7.
    发明申请
    VIDEO PROCESSING SYSTEM, VIDEO PROCESSING METHOD, VIDEO PROCESSING APPARATUS, CONTROL METHOD OF THE APPARATUS, AND STORAGE MEDIUM STORING CONTROL PROGRAM OF THE APPARATUS 审中-公开
    视频处理系统，视频处理方法，视频处理设备，设备的控制方法和存储设备的存储控制程序

    公开(公告)号：US20140010521A1

    公开(公告)日：2014-01-09

    申请号：US14007245

    申请日：2012-01-30

    申请人： Hiroo Harada ,  Naotake Fujita

    发明人： Hiroo Harada ,  Naotake Fujita

    IPC分类号： H04N5/91

    CPC分类号： H04N5/91 ,  G06F16/71 ,  G06F16/7847 ,  H04N21/23418 ,  H04N21/235 ,  H04N21/266 ,  H04N21/4722 ,  H04N21/4882 ,  H04N21/8133 ,  H04N21/84

    摘要： A system of this invention is a video processing system for outputting additional information to be added to a video content. This video processing system includes a frame feature extractor that extracts a frame feature of a frame included in an arbitrary video content, a video content extractor that extracts a video content group having a scene formed from a series of a plurality of frames in the arbitrary video content by comparing frame features of the arbitrary video content extracted by the frame feature extractor with frame features of another video contents, the video content group including an original video content with the scene unaltered and one or more derivative video contents with the scene altered, and an additional information extractor that extracts additional information added to the scene of the extracted video content group. With this arrangement, additional information added to a video content group including an identical scene can be referred to from one video content.

    摘要翻译： 本发明的系统是用于输出要添加到视频内容的附加信息的视频处理系统。 该视频处理系统包括提取包含在任意视频内容中的帧的帧特征的帧特征提取器，提取具有由任意视频中的多个帧的一系列构成的场景的视频内容组的视频内容提取器 通过将由帧特征提取器提取的任意视频内容的帧特征与另一视频内容的帧特征进行比较，所述视频内容组包括与所述场景不一致的原始视频内容和所述场景改变的一个或多个导出视频内容，以及 附加信息提取器，其提取添加到所提取的视频内容组的场景中的附加信息。 利用这种安排，可以从一个视频内容中引用添加到包括相同场景的视频内容组的附加信息。

    Method and apparatus for active annotation of multimedia content
    8.
    发明申请
    Method and apparatus for active annotation of multimedia content 审中-公开
    用于主动注释多媒体内容的方法和装置

    公开(公告)号：US20040205482A1

    公开(公告)日：2004-10-14

    申请号：US10056546

    申请日：2002-01-24

    申请人： International Business Machines Corporation

    发明人： Sankar Basu ,  Ching-Yung Lin ,  Milind R. Naphade ,  John R. Smith ,  Belle L. Tseng

    IPC分类号： G06F017/24

    CPC分类号： G11B27/34 ,  G06F16/78 ,  G06F16/7834 ,  G06F16/7847 ,  G06F17/241 ,  G11B27/105 ,  G11B27/28

    摘要： Semantic indexing and retrieval of multimedia content requires that the content is sufficiently annotated. However, the great volumes of multimedia data and diversity of labels make annotation a difficult and costly process. Disclosed is an annotation framework in which supervised training with partially labeled data is facilitated using active learning. The system trains a classifier with a small set of labeled data and subsequently updates the classifier by selecting a subset of the available data-set according to optimization criteria. The process results in propagation of labels to unlabeled data and greatly facilitates the user in annotating large amounts of multimedia content.

    摘要翻译： 多媒体内容的语义索引和检索要求内容充分注释。 然而，大量的多媒体数据和标签的多样性使得注释成为一个困难和昂贵的过程。 公开了一种注释框架，其中使用主动学习便于使用部分标记数据的监督训练。 系统训练具有一小组标记数据的分类器，随后根据优化标准选择可用数据集的子集来更新分类器。 该过程导致标签传播到未标记的数据，并大大方便用户注释大量的多媒体内容。

    Digital media recognition apparatus and methods
    9.
    发明申请
    Digital media recognition apparatus and methods 有权
    数字媒体识别装置及方法

    公开(公告)号：US20040133927A1

    公开(公告)日：2004-07-08

    申请号：US10416560

    申请日：2003-05-12

    发明人： Stanley Sternberg ,  William Dargel ,  John W Lennington ,  Thomas Voiles

    IPC分类号： H04N007/16 ,  H04B001/66 ,  H04N007/12 ,  H04N011/02 ,  H04N011/04 ,  H04N007/00 ,  H04N011/00 ,  H04N005/445

    CPC分类号： G06K9/00624 ,  G06F16/583 ,  G06F16/7328 ,  G06F16/7847 ,  G06K9/00711 ,  G06K9/52

    摘要： Physical objects, including still and moving images, sound/audio and text are transformed into more compact forms for identification and other purposes using a method unrelated to existing image-matching systems which rely on feature extraction. An auxiliary construct, preferably a warp grid, is associated with an object, and a series of transformations are imposed to generate a unique visual key for identification, comparisons, and other operations. Search methods are also disclosed for matching an unknown image to one previously represented in a visual key database. Broadly, a preferred search method sequentially examines candidate database images for their closeness of match in a sequential order determined by their a priori match probability. Thus, the most likely match candidate is examined first, the next most likely second, and so forth. With respect to the recognition of video sequences and other information streams, inventive holotropic stream recognition principles are deployed, wherein the statistics of the spatial distribution of warp grid points is used to generate index keys. The invention is applicable to various fields of endeavor, including governmental, scientific, industrial, commercial, and recreational object identification and information retrieval. Extensions of the technology are also disclosed to achieve a uniform distribution of objects over the database search, a consideration which is central to scalability. In particular, a generalized method has been developed based on reticle projection, which greatly enhances the uniformity of object distributions in the collected data Thus, whereas statistical criteria are used with respect to particular embodiments in transforming a construct associated with an image, audio, text or other representation, a reticle projection may alternatively be used in attribute transformation according to alternative embodiments of the invention.

    摘要翻译： 使用与依赖于特征提取的现有图像匹配系统无关的方法，物理对象（包括静止和运动图像）的声音/音频和文本被转换成更紧凑的形式用于识别和其他目的。 一个辅助结构，优选一个经线网格，与一个对象相关联，并进行一系列变换以产生用于识别，比较和其他操作的唯一视觉键。 还公开了搜索方法，用于将未知图像与先前在视觉密钥数据库中表示的图像进行匹配。 广义上，优选的搜索方法按照先验匹配概率确定的顺序顺序地检查候选数据库图像的匹配接近度。 因此，首先检查最有可能的匹配候选者，接下来最可能的第二个等等。 关于视频序列和其他信息流的识别，部署了本发明的旋转数据流识别原理，其中使用经线网格点的空间分布的统计来生成索引关键字。 本发明适用于政府，科学，工业，商业，娱乐对象识别和信息检索等各个领域。 还公开了该技术的扩展，以实现数据库搜索中对象的均匀分布，这是可扩展性的核心。 特别地，已经基于掩模版投影开发了广义的方法，这大大增强了所收集的数据中的对象分布的均匀性。因此，尽管统计标准被用于转换与图像，音频，文本相关联的特定实施例 或其他表示，根据本发明的替代实施例，标线投影可以替代地用于属性变换。

    Image indexing systems
    10.
    发明申请
    Image indexing systems 失效
    图像索引系统

    公开(公告)号：US20030147623A1

    公开(公告)日：2003-08-07

    申请号：US10220954

    申请日：2002-11-25

    发明人： Ian Fletcher

    IPC分类号： H04N009/79

    CPC分类号： G06F16/7847

    摘要： An image indexing system comprising a video frame store, an averager which provides a first signal indicative of the average brightness level of each frame stored, an image splitter and averager which divides each frame into contiguous blocks of pixels, and provides for each block, a second signal indicative of its average brightness level, a comparator which compares each of the second signals with the first signal so as to produce in respect of each block a binary signal indicative of whether or not its brightness level, as indicated by the first signal, is greater or less than the average brightness level for the frame as indicated by the first signal, thereby to produce for each frame, an index signal comprising one binary bit for each block which serves to identify each frame for indexing purposes.

    摘要翻译： 一种图像索引系统，包括视频帧存储器，平均器，其提供指示存储的每个帧的平均亮度级别的第一信号;图像分离器和平均器，其将每个帧划分成连续的像素块，并且为每个块提供一个 指示其平均亮度级的第二信号，比较器，其将每个第二信号与第一信号进行比较，以便针对每个块产生指示其亮度级别（如第一信号所指示）是否为二进制信号的二进制信号， 大于或小于由第一信号指示的帧的平均亮度级，从而为每个帧产生索引信号，该索引信号包括用于每个块的一个二进制位，用于识别每个帧用于索引目的。