-
公开(公告)号：US20170017861A1
公开(公告)日：2017-01-19
申请号：US14802089
申请日：2015-07-17
Applicant: XEROX CORPORATION
Inventor： Sonal S. Patil , Kundan Shrivastava , Om D. Deshmukh
CPC classification number: G06K9/6253 , H04N21/234336 , H04N21/251 , H04N21/25891 , H04N21/8456 , H04N21/8547
Abstract: The disclosed embodiments relate to a method for content recommendation. The method includes determining, by one or more processors, one or more features of a segment of a first content being accessed during a presentation of the first content on a user-computing device. The segment of the first content is accessed for a predetermined number of times. The method further includes extracting for a feature from the one or more features, a second content based on the feature, wherein the second content is recommended through the user-computing device.
Abstract translation: 所公开的实施例涉及用于内容推荐的方法。 该方法包括由一个或多个处理器确定在用户计算设备上呈现第一内容期间被访问的第一内容的段的一个或多个特征。 访问第一内容的片段预定次数。 所述方法还包括从所述一个或多个特征提取特征，基于所述特征提取第二内容，其中通过所述用户计算设备推荐所述第二内容。
-
Patent Agency Ranking
公开(公告)号：US20160307563A1
公开(公告)日：2016-10-20
申请号：US14687042
申请日：2015-04-15
Applicant: XEROX CORPORATION
Inventor： Kundan Shrivastava , Om D. Deshmukh , Geetha Manjunath
CPC classification number: G06F17/2775 , G06F16/951 , G10L15/26
Abstract: The disclosed embodiments illustrate methods and systems for detecting plagiarism in a conversation. The method includes receiving first input corresponding to a query from a first user in said conversation. The first input corresponds to at least a first audio signal received from said first user. The method includes receiving second input corresponding to one or more responses received from a second user in response to said query. The second input corresponds to at least a second audio signal received from said second user. Thereafter, the method includes determining a first score for one or more websites, based on a comparison between said one or more responses and content obtained from said one or more websites in response to said query. The first score is a measure of a similarity between said one or more responses and said content. The method is performed by one or more microprocessors.
Abstract translation: 所公开的实施例示出了用于在对话中检测剽窃的方法和系统。 该方法包括在所述对话中从第一用户接收与查询对应的第一输入。 第一输入对应于从所述第一用户接收的至少第一音频信号。 所述方法包括响应于所述查询接收对应于从第二用户接收的一个或多个响应的第二输入。 第二输入对应于从所述第二用户接收的至少第二音频信号。 此后，该方法包括基于所述一个或多个响应之间的比较以及响应于所述查询从所述一个或多个网站获得的内容来确定一个或多个网站的第一分数。 第一分数是所述一个或多个响应和所述内容之间的相似度的度量。 该方法由一个或多个微处理器执行。
-
公开(公告)号：US09484032B2
公开(公告)日：2016-11-01
申请号：US14523966
申请日：2014-10-27
Applicant: XEROX CORPORATION
Inventor： Kuldeep Yadav , Kundan Shrivastava , Om D Deshmukh
CPC classification number: G10L15/26 , G06F3/04842 , G06F17/28 , G06F17/30026 , G10L15/1807 , G10L21/10 , G10L25/57 , G10L2015/088
Abstract: The disclosed embodiments illustrate methods and systems for processing multimedia content. The method includes extracting one or more words from an audio stream associated with multimedia content. Each word has associated one or more timestamps indicative of temporal occurrences of said word in said multimedia content. The method further includes creating a word cloud of said one or more words in said multimedia content based on a measure of emphasis laid on each word in said multimedia content and said one or more timestamps associated with said one or more words. The method further includes presenting one or more multimedia snippets, of said multimedia content, associated with a word selected by a user from said word cloud. Each of said one or more multimedia snippets corresponds to said one or more timestamps associated with occurrences of said word in said multimedia content.
Abstract translation: 所公开的实施例示出了用于处理多媒体内容的方法和系统。 该方法包括从与多媒体内容相关联的音频流中提取一个或多个单词。 每个单词具有指示所述多媒体内容中所述单词的时间出现的一个或多个时间戳。 所述方法还包括基于所述多媒体内容中的每个单词的重点测量以及与所述一个或多个单词相关联的所述一个或多个时间戳来创建所述多媒体内容中的所述一个或多个单词的单词云。 该方法还包括呈现与所述词云选择的一个词相关联的所述多媒体内容的一个或多个多媒体片段。 所述一个或多个多媒体片段中的每一个对应于与所述多媒体内容中的所述单词的出现相关联的所述一个或多个时间戳。
-
公开(公告)号：US20160118060A1
公开(公告)日：2016-04-28
申请号：US14523966
申请日：2014-10-27
Applicant: XEROX CORPORATION
Inventor： Kuldeep Yadav , Kundan Shrivastava , Om D. Deshmukh
IPC: G10L25/57 , G10L15/26 , G10L15/22 , G06F3/0484 , G10L15/18
CPC classification number: G10L15/26 , G06F3/04842 , G06F17/28 , G06F17/30026 , G10L15/1807 , G10L21/10 , G10L25/57 , G10L2015/088
Abstract: The disclosed embodiments illustrate methods and systems for processing multimedia content. The method includes extracting one or more words from an audio stream associated with multimedia content. Each word has associated one or more timestamps indicative of temporal occurrences of said word in said multimedia content. The method further includes creating a word cloud of said one or more words in said multimedia content based on a measure of emphasis laid on each word in said multimedia content and said one or more timestamps associated with said one or more words. The method further includes presenting one or more multimedia snippets, of said multimedia content, associated with a word selected by a user from said word cloud. Each of said one or more multimedia snippets corresponds to said one or more timestamps associated with occurrences of said word in said multimedia content.
Abstract translation: 所公开的实施例示出了用于处理多媒体内容的方法和系统。 该方法包括从与多媒体内容相关联的音频流中提取一个或多个单词。 每个单词具有指示所述多媒体内容中所述单词的时间出现的一个或多个时间戳。 所述方法还包括基于所述多媒体内容中的每个单词的重点测量以及与所述一个或多个单词相关联的所述一个或多个时间戳来创建所述多媒体内容中的所述一个或多个单词的单词云。 该方法还包括呈现与所述词云选择的一个词相关联的所述多媒体内容的一个或多个多媒体片段。 所述一个或多个多媒体片段中的每一个对应于与所述多媒体内容中的所述单词的出现相关联的所述一个或多个时间戳。
-
公开(公告)号：US09785834B2
公开(公告)日：2017-10-10
申请号：US14798499
申请日：2015-07-14
Applicant: XEROX CORPORATION
Inventor： Arijit Biswas , Harish Arsikere , Kundan Shrivastava , Om D Deshmukh
CPC classification number: G06K9/00577 , G06F17/3079 , G06K9/00302 , G06K9/00362 , G06K9/00751
Abstract: According to embodiments illustrated herein, a method and system is provided for indexing a multimedia content. The method includes extracting, by one or more processors, a set of frames from the multimedia content, wherein the set of frames comprises at least one of a human object and an inanimate object. Thereafter, a body language information pertaining to the human object is determined from the set of frames by utilizing one or more image processing techniques. Further, an interaction information is determined from the set of frames. The interaction information is indicative of an action performed by the human object on the inanimate object. Thereafter, the multimedia content is indexed in a content database based at least on the body language information and the interaction information.
-
公开(公告)号：US20170017838A1
公开(公告)日：2017-01-19
申请号：US14798499
申请日：2015-07-14
Applicant: XEROX CORPORATION
Inventor： Arijit Biswas , Harish Arsikere , Kundan Shrivastava , Om D. Deshmukh
CPC classification number: G06K9/00577 , G06F17/3079 , G06K9/00302 , G06K9/00362 , G06K9/00751
Abstract: According to embodiments illustrated herein, a method and system is provided for indexing a multimedia content. The method includes extracting, by one or more processors, a set of frames from the multimedia content, wherein the set of frames comprises at least one of a human object and an inanimate object. Thereafter, a body language information pertaining to the human object is determined from the set of frames by utilizing one or more image processing techniques. Further, an interaction information is determined from the set of frames. The interaction information is indicative of an action performed by the human object on the inanimate object. Thereafter, the multimedia content is indexed in a content database based at least on the body language information and the interaction information.
Abstract translation: 根据本文所示的实施例，提供了一种用于索引多媒体内容的方法和系统。 该方法包括由一个或多个处理器提取来自多媒体内容的一组帧，其中该组帧包括人类对象和无生命对象中的至少一个。 此后，通过利用一个或多个图像处理技术从该组帧确定与人类对象有关的身体语言信息。 此外，从该组帧确定交互信息。 交互信息指示人类对象在无生命物体上执行的动作。 此后，多媒体内容至少基于身体语言信息和交互信息被索引到内容数据库中。
-
-
-
-
-
Search Results
6
records
(took 0.014 seconds)
