Real-time duplicate detection for uploaded videos
    2.
    发明授权
    Real-time duplicate detection for uploaded videos 有权
    上传视频的实时重复检测

    公开(公告)号:US08953836B1

    公开(公告)日:2015-02-10

    申请号:US13363116

    申请日:2012-01-31

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00758

    摘要: Systems and methods are provided herein relating to real-time duplicate detection of video content. Fingerprints can be generated for an uploaded video. The fingerprints can be used to match the uploaded video to a set of matching videos. The set of matching videos can be filtered based on the type of match, and the quality of the match. A unique cluster-id can be generated for the uploaded video containing an upload time, and that unique cluster-id can then be modified to associate the uploaded video with a cluster-id of potential duplicates. Cluster-ids can then be used in the context of a search to filter results that have identical cluster-ids. The benefits in using real-time duplicate detection can better maximize user experiences in a video sharing service that contains potential duplicates of the same content.

    摘要翻译: 本文提供了与视频内容的实时重复检测有关的系统和方法。 可以为上传的视频生成指纹。 指纹可用于将上传的视频与一组匹配的视频相匹配。 匹配视频的集合可以根据匹配的类型和匹配的质量进行过滤。 可以为包含上传时间的上传视频生成唯一的cluster-id,然后可以修改唯一的cluster-id,将上传的视频与可能重复的集群ID相关联。 然后可以在搜索的上下文中使用Cluster-id来过滤具有相同集群ids的结果。 使用实时重复检测的好处可以更好地最大限度地最大限度地增加包含相同内容的潜在重复性的视频共享服务中的用户体验。

    Video segment identification and organization based on dynamic characterizations
    3.
    发明授权
    Video segment identification and organization based on dynamic characterizations 有权
    基于动态特征的视频段识别和组织

    公开(公告)号:US08942542B1

    公开(公告)日:2015-01-27

    申请号:US13611675

    申请日:2012-09-12

    IPC分类号: H04N9/80

    摘要: This disclosure relates to video segment identification and organization based on dynamic characterizations. A characteristics component analyzes a video, and determines a set of video characteristics based at least in part on the analysis. The video characteristics include but are not limited to a category, a type, an identity of a person, and/or an identity of an object. A segmenting component segments the video based in part on the set of video characteristics, and an indicator component associates indicators corresponding to respective video characteristics with the corresponding video segments.

    摘要翻译: 本公开涉及基于动态特征的视频段识别和组织。 特征部件分析视频,并且至少部分地基于分析来确定一组视频特征。 视频特征包括但不限于类别,类型,个人身份和/或对象的身份。 分割组件部分地基于视频特征集分割视频,并且指示符组件将对应于各个视频特征的指示符与相应的视频段相关联。