公开(公告)号：US09888279B2

公开(公告)日：2018-02-06

申请号：US14483507

申请日：2014-09-11

申请人： ARRIS Enterprises, Inc.

发明人： Faisal Ishtiaq ,  Benedito J. Fonseca, Jr. ,  Kevin L. Baum ,  Anthony J. Braskich ,  Stephen P. Emeott ,  Bhavan Gandhi ,  Renxiang Li ,  Alfonso Martinez Smith ,  Michael L. Needham ,  Isselmou Ould Dellahy

IPC分类号： H04N5/445 ,  H04N21/431 ,  H04N21/234 ,  H04N21/235 ,  H04N21/482 ,  H04N21/488 ,  H04N21/81 ,  G06K9/00

CPC分类号： H04N21/4316 ,  G06K9/00711 ,  G06K9/00765 ,  G06K2209/27 ,  H04N21/23418 ,  H04N21/2353 ,  H04N21/4828 ,  H04N21/4884 ,  H04N21/812

摘要： A method receives video content and metadata associated with video content. The method then extracts features of the video content based on the metadata. Portions of the visual, audio, and textual features are fused into composite features that include multiple features from the visual, audio, and textual features. A set of video segments of the video content is identified based on the composite features of the video content. Also, the segments may be identified based on a user query.

公开(公告)号：US20150082349A1

公开(公告)日：2015-03-19

申请号：US14483507

申请日：2014-09-11

申请人： ARRIS Enterprises, Inc.

发明人： Faisal Ishtiaq ,  Benedito J. Fonseca, JR. ,  Kevin L. Baum ,  Anthony J. Braskich ,  Stephen P. Emeott ,  Bhavan Gandhi ,  Renxiang Li ,  Alfonso Martinez Smith ,  Michael L. Needham ,  Isselmou Ould Dellahy

IPC分类号： H04N21/431 ,  H04N21/81 ,  H04N21/234 ,  H04N21/235 ,  H04N21/488 ,  H04N21/482

CPC分类号： H04N21/4316 ,  G06K9/00711 ,  G06K9/00765 ,  G06K2209/27 ,  H04N21/23418 ,  H04N21/2353 ,  H04N21/4828 ,  H04N21/4884 ,  H04N21/812

摘要： A method receives video content and metadata associated with video content. The method then extracts features of the video content based on the metadata. Portions of the visual, audio, and textual features are fused into composite features that include multiple features from the visual, audio, and textual features. A set of video segments of the video content is identified based on the composite features of the video content. Also, the segments may be identified based on a user query.

摘要翻译： 一种方法接收与视频内容相关联的视频内容和元数据。 该方法然后基于元数据提取视频内容的特征。 视觉，音频和文字功能的部分融合到复合功能中，包括视觉，音频和文字功能的多个功能。 基于视频内容的复合特征来识别视频内容的一组视频片段。 此外，可以基于用户查询来标识段。