公开(公告)号：US20140229472A1

公开(公告)日：2014-08-14

申请号：US14176482

申请日：2014-02-10

Applicant: THOMSON LICENSING

Inventor： Marie GUEGAN ,  James Lanagan ,  Philippe Schmouker ,  Anne Lambert

IPC: G06F17/30

CPC classification number: G06F16/447 ,  H04N21/4307 ,  H04N21/4788 ,  H04N21/84 ,  H04N21/8547

Abstract: The invention concerns a method for enriching a multimedia content defined by a timeline and by a chronological text description, wherein it comprises the following steps of: identifying using natural language processing at least one feature in at least a part of a text document retrieved from a network, automatically aligning said determined part of the text document to at least a part of the chronological text description, which semantically corresponds to said determined part of the text document, so that at least the part of the text document is automatically synchronized with the timeline of the multimedia content, the chronological text description being itself synchronized with the timeline.

Abstract translation: 本发明涉及一种用于丰富由时间线和按时间顺序的文本描述定义的多媒体内容的方法，其中包括以下步骤：使用自然语言处理识别至少一部分从 网络，将所述确定的文本文档的所述部分自动对准所述时间文本描述的至少一部分，其在语义上对应于所述确定的文本文档的部分，使得文本文档的至少部分与时间线自动同步 多媒体内容的时间顺序文本描述本身与时间线同步。

公开(公告)号：US20180368684A1

公开(公告)日：2018-12-27

申请号：US16064603

申请日：2016-12-20

Applicant: THOMSON Licensing

Inventor： Philippe SCHMOUKER ,  Christopher HOWSON ,  Serge DEFRANCE ,  Eric GAUTIER ,  Marie GUEGAN

IPC: A61B5/00 ,  H04L29/08 ,  G08B21/18

Abstract: A system and method are provided for detecting a behavior patterns of a user. In one embodiment, the method comprises receiving information about activities of a user and calculating duration of each activity. Each activity that exceeds a threshold duration is categorized and labelled accordingly. Activities with similar labels are grouped and labelled activities are analyzing. Alerts are then generated for certain behavioral patterns such as those exhibiting anomalies.

公开(公告)号：US20170337913A1

公开(公告)日：2017-11-23

申请号：US15527174

申请日：2016-11-24

Applicant: THOMSON LICENSING

Inventor： Marie GUEGAN ,  Alexey OZEROV

IPC: G10H1/36 ,  G10L21/10 ,  G10L21/055 ,  G10L15/26 ,  G10L15/14

CPC classification number: G10H1/361 ,  G10H2220/011 ,  G10H2250/015 ,  G10L15/142 ,  G10L15/26 ,  G10L21/055 ,  G10L21/10

Abstract: An apparatus and method for generating visual content from an audio signal are described. The method includes receiving (310) audio content, processing (320) the audio content to separate into a first and second portion of the audio content, converting (330) the second portion into visual content, delaying (340) the first portion based on a time relationship between the audio content and the visual content, the delaying accounting for time to process the first portion and convert the second portion, and providing (350) the visual content and audio content for reproduction. The apparatus includes a source separation module (210) processing the received audio content to separate into a first and second portion of the audio content, a converter module (220) converting the second portion into visual content, and a synchronization module (230) delaying the first portion based on a time relationship between the audio content and the visual content.

公开(公告)号：US20180210954A1

公开(公告)日：2018-07-26

申请号：US15322442

申请日：2015-06-25

Applicant: THOMSON LICENSING

Inventor： Marie GUEGAN ,  Philippe SCHMOUKER

IPC: G06F17/30 ,  G06Q50/00

CPC classification number: G06F16/739 ,  G06F16/3331 ,  G06Q50/01

Abstract: An automated creation of a summary video based on video segments extracted from several videos by using a social network of viewers and a social curve specified by a user in order to select and order the video segments. A social network of viewers (influence scores, experts) may be used to establish metrics for video segments. A social curve may be defined with respect to the video segment metrics to allow for the automatic creation of a summary video.

公开(公告)号：US20150058346A1

公开(公告)日：2015-02-26

申请号：US14461486

申请日：2014-08-18

Applicant: THOMSON LICENSING

Inventor： Marie GUEGAN ,  James LANAGAN ,  Frederic PLISSONNEAU

IPC: G06F17/30

CPC classification number: G06F17/3002 ,  G06F17/30044

Abstract: The invention concerns a device (D) for assigning time information to a main multimedia content related to a given object. To this end, said device comprises: a clustering module (4) configured to cluster a set of auxiliary multimedia contents with time information and related to said object, so as to deliver clusters comprising some of said auxiliary multimedia contents; a determining module (5) configured to determine a time data for each cluster; a computing module (6) configured to compute a distance between the main multimedia content and each of said clusters, an assigning module (7) configured to assign to the main multimedia content, the time data of the cluster having the smallest distance said amongst computed distances.

Abstract translation: 本发明涉及一种用于将时间信息分配给与给定对象相关的主要多媒体内容的设备（D）。 为此，所述设备包括：聚集模块（4），被配置为使一组辅助多媒体内容与时间信息聚集并与所述对象相关，以便传送包括所述辅助多媒体内容中的一些的集群; 确定模块（5），被配置为确定每个簇的时间数据; 计算模块（6），其被配置为计算所述主多媒体内容与所述群集中的每一个之间的距离;分配模块（7），被配置为向所述主多媒体内容分配所计算的所述群集之间具有最小距离的所述群集的时间数据 距离

公开(公告)号：US20150019555A1

公开(公告)日：2015-01-15

申请号：US14329018

申请日：2014-07-11

Applicant: THOMSON LICENSING

Inventor： James LANAGAN ,  Marie GUEGAN ,  Philippe SCHMOUKER

IPC: G06F17/30

CPC classification number: G06F17/30017 ,  G06F17/30056

Abstract: According to the invention, the method comprises the following steps of: clustering said plurality of creators to deliver clusters comprising at least two creators, called relevant creators; assigning, to at least some relevant creators of the cluster comprising the first creator, called first cluster, a score of relevance determined from at least one criterion of similarity between said relevant creators and said first creator; ranking relevant creators of said first cluster according to their scores of relevance; selecting, among a plurality of multimedia contents, at least one second multimedia content related to said first multimedia content and delivered by a ranked relevant creator of said first cluster; enriching said first multimedia content based on said second multimedia content.

Abstract translation: 根据本发明，该方法包括以下步骤：将所述多个创建者聚类以传递包括至少两个称为相关创建者的创建者的群集; 向包括第一创建者的群集的至少一些相关创建者分配被称为第一群集的相关创建者，根据所述相关创建者和所述第一创建者之间的至少一个相似标准确定相关得分; 根据其相关分数对所述第一集群的相关创造者进行排名; 在多个多媒体内容中选择与所述第一多媒体内容相关并由所述第一集群的排名相关的创建者交付的至少一个第二多媒体内容; 基于所述第二多媒体内容丰富所述第一多媒体内容。