专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11409791B2 Joint heterogeneous language-vision embeddings for video tagging and search 有权
公开(公告)号：US11409791B2
公开(公告)日：2022-08-09
申请号：US15620232
申请日：2017-06-12
申请人： Disney Enterprises, Inc.
发明人： Atousa Torabi , Leonid Sigal
IPC分类号： G06F16/638 , G06N3/08 , G06N3/04 , H04N21/8405 , G06F16/783 , G06V20/40
摘要： Systems, methods and articles of manufacture for modeling a joint language-visual space. A textual query to be evaluated relative to a video library is received from a requesting entity. The video library contains a plurality of instances of video content. One or more instances of video content from the video library that correspond to the textual query are determined, by analyzing the textual query using a data model that includes a soft-attention neural network module that is jointly trained with a language Long Short-term Memory (LSTM) neural network module and a video LSTM neural network module. At least an indication of the one or more instances of video content is returned to the requesting entity.

2. 发明授权

US10482329B2 Systems and methods for identifying activities and/or events in media contents based on object data and scene data 有权
公开(公告)号：US10482329B2
公开(公告)日：2019-11-19
申请号：US15908617
申请日：2018-02-28
申请人： Disney Enterprises, Inc.
发明人： Zuxuan Wu , Yanwei Fu , Leonid Sigal
IPC分类号： G06K9/00 , H04L29/06 , G06K9/46 , G06T7/62 , G06T7/90 , G11B27/10 , G06N3/04 , G06N3/08
摘要： There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive a plurality of training contents depicting a plurality of activities, extract training object data from the plurality of training contents including a first training object data corresponding to a first activity, extract training scene data from the plurality of training contents including a first training scene data corresponding to the first activity, determine that a probability of the first activity is maximized when the first training object data and the first training scene data both exist in a sample media content.

3. 发明授权

US10223580B2 Methods and systems for action recognition using poselet keyframes 有权
公开(公告)号：US10223580B2
公开(公告)日：2019-03-05
申请号：US14025722
申请日：2013-09-12
申请人： Disney Enterprises, Inc.
发明人： Michail Raptis , Leonid Sigal
IPC分类号： G06K9/00 , G06K9/62 , H04N5/33 , G06K9/46
摘要： Methods and systems for video action recognition using poselet keyframes are disclosed. An action recognition model may be implemented to spatially and temporally model discriminative action components as a set of discriminative keyframes. One method of action recognition may include the operations of selecting a plurality of poselets that are components of an action, encoding each of a plurality of video frames as a summary of the detection confidence of each of the plurality of poselets for the video frame, and encoding correlations between poselets in the encoded video frames.

4. 发明申请

US20170308756A1 Systems and Methods for Identifying Activities in Media Contents Based on Prediction Confidences 审中-公开
公开(公告)号：US20170308756A1
公开(公告)日：2017-10-26
申请号：US15210708
申请日：2016-07-14
申请人： Disney Enterprises, Inc.
发明人： Leonid Sigal , Shugao Ma
IPC分类号： G06K9/00 , H04L29/06
CPC分类号： G06K9/00751 , G06K9/00335 , G06K9/00671 , G06K9/00718 , G06K9/00744 , G06K9/4628 , G06K2009/00738 , G06K2209/21 , G06T7/62 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G11B27/10 , H04L65/4069
摘要： There is provided a system comprising a memory and a processor configured to receive a media content depicting an activity, extract a first plurality of features from a first segment of the media content, make a first prediction that the media content depicts a first activity based on the first plurality of features, wherein the first prediction has a first confidence level, extract a second plurality of features from a second segment of the media content, the second segment temporally following the first segment in the media content, make a second prediction that the media content depicts the first activity based on the second plurality of features, wherein the second prediction has a second confidence level, determine that the media content depicts the first activity based on the first prediction and the second prediction, wherein the second confidence level is at least as high as the first confidence level.

5. 发明申请

US20170308754A1 Systems and Methods for Determining Actions Depicted in Media Contents Based on Attention Weights of Media Content Frames 审中-公开
公开(公告)号：US20170308754A1
公开(公告)日：2017-10-26
申请号：US15202471
申请日：2016-07-05
申请人： Disney Enterprises, Inc.
发明人： Atousa Torabi , Leonid Sigal
IPC分类号： G06K9/00 , G11B27/10
CPC分类号： G06K9/00751 , G06K9/00335 , G06K9/00671 , G06K9/00718 , G06K9/00744 , G06K9/4628 , G06K2009/00738 , G06K2209/21 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06T7/62 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G11B27/102 , H04L65/4069
摘要： There is provided a system comprising a label database including a plurality of label, a non-transitory memory storing an executable code, and a hardware processor executing the executable code to receive a media content including a plurality of segments, each segment including a plurality of frames, extract a first plurality of features from a segment, extract a second plurality of features from each frame of the segment, determine an attention weight for each frame of the segment based on the first plurality of features extracted from the segment and the second plurality of features extracted from the segment, and determine that the segment depicts one of the plurality of labels in a label database based on the first plurality of features, the second plurality of features, and the attention weight of each frame of the plurality of frames of the segment.

6. 发明申请

US20160292538A1 Object Classification Through Semantic Mapping 有权
标题翻译：通过语义映射进行对象分类
公开(公告)号：US20160292538A1
公开(公告)日：2016-10-06
申请号：US14675268
申请日：2015-03-31
申请人： Disney Enterprises, Inc.
发明人： Sung Ju Hwang , Jonghyun Choi , Leonid Sigal
IPC分类号： G06K9/62
CPC分类号： G06K9/6269 , G06K9/628 , G06K9/6286
摘要： There are provided systems and methods for performing object classification through semantic mapping. Such an object classification system includes a system processor, a system memory, and an object categorizing unit stored in the system memory. The system processor is configured to execute the object categorizing unit to receive image data corresponding to an object, and to transform the image data into a directed quantity expressed at least in part in terms of semantic parameters. The system processor is further configured to determine a projection of the directed quantity onto an object representation map including multiple object categories, and to associate the object with a category from among the multiple object categories based on the projection.
摘要翻译：提供了通过语义映射来执行对象分类的系统和方法。这样的对象分类系统包括系统处理器，系统存储器和存储在系统存储器中的对象分类单元。系统处理器被配置为执行对象分类单元以接收与对象相对应的图像数据，并且将图像数据变换成至少部分地根据语义参数表达的定向量。系统处理器还被配置为确定定向量的投影到包括多个对象类别的对象表示图上，并且基于投影将对象与多个对象类别中的类别相关联。

7. 发明授权

US09317782B2 Incremental category embedding for categorization 有权
标题翻译：增量类别嵌入进行分类
公开(公告)号：US09317782B2
公开(公告)日：2016-04-19
申请号：US14485537
申请日：2014-09-12
申请人： Disney Enterprises, Inc.
发明人： Sung Ju Hwang , Leonid Sigal
IPC分类号： G06K9/00 , G06E1/00 , G06K9/62 , G06N99/00
CPC分类号： G06N99/005 , G06K9/6255
摘要： There are provided systems and methods of incremental category embedding for categorization. One method including selecting one or more input categories from a plurality of input categories to be added to learned categories, determining at least one representative category from the learned categories for each input category from the one or more input categories, the at least one representative category representing the input category, and approximating the input category using the at least one representative category.
摘要翻译：提供了用于分类的增量类别嵌入的系统和方法。一种方法，包括从多个输入类别中选择一个或多个输入类别以添加到所学习的类别，从所述一个或多个输入类别的每个输入类别的学习类别中确定至少一个代表类别，所述至少一个代表类别代表输入类别，并使用至少一个代表类别近似输入类别。

8. 发明授权

US10956685B2 Alignment of video and textual sequences for metadata analysis 有权
公开(公告)号：US10956685B2
公开(公告)日：2021-03-23
申请号：US16786804
申请日：2020-02-10
申请人： Disney Enterprises, Inc.
发明人： Boyang Li , Leonid Sigal , Pelin Dogan
IPC分类号： G06F40/45 , G06K9/00 , G06K9/62 , G06N5/04
摘要： Systems, methods and computer program products related to aligning heterogeneous sequential data are disclosed. Video data in a media presentation and textual data corresponding to content of the media presentation are received. An action related to aligning the video data and the textual data is determined using an alignment neural network, such that the video data and the textual data are at least partially aligned following the action. The alignment neural network includes a first fully connected layer that receives as input the video data, the textual data, and data relating to a previously determined action by the alignment neural network related to aligning the video data and the textual data. The determined action related to aligning the video data and the textual data is performed.

9. 发明申请

US20180189569A1 Systems and Methods for Identifying Activities and/or Events in Media Contents Based on Object Data and Scene Data 审中-公开
公开(公告)号：US20180189569A1
公开(公告)日：2018-07-05
申请号：US15908617
申请日：2018-02-28
申请人： Disney Enterprises, Inc.
发明人： Zuxuan Wu , Yanwei Fu , Leonid Sigal
IPC分类号： G06K9/00
CPC分类号： G06K9/00751 , G06K9/00335 , G06K9/00671 , G06K9/00718 , G06K9/00744 , G06K9/4628 , G06K2009/00738 , G06K2209/21 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06T7/62 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G11B27/102 , H04L65/4069
摘要： There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive a plurality of training contents depicting a plurality of activities, extract training object data from the plurality of training contents including a first training object data corresponding to a first activity, extract training scene data from the plurality of training contents including a first training scene data corresponding to the first activity, determine that a probability of the first activity is maximized when the first training object data and the first training scene data both exist in a sample media content.

10. 发明授权

US09940522B2 Systems and methods for identifying activities and/or events in media contents based on object data and scene data 有权
公开(公告)号：US09940522B2
公开(公告)日：2018-04-10
申请号：US15211403
申请日：2016-07-15
申请人： Disney Enterprises, Inc.
发明人： Zuxuan Wu , Yanwei Fu , Leonid Sigal
IPC分类号： G06K9/00
CPC分类号： G06K9/00751 , G06K9/00335 , G06K9/00671 , G06K9/00718 , G06K9/00744 , G06K9/4628 , G06K2009/00738 , G06K2209/21 , G06T7/62 , G06T7/90 , G06T2207/10016 , G06T2207/10024 , G06T2207/20081 , G06T2207/20084 , G11B27/10 , H04L65/4069
摘要： There is provided a system including a non-transitory memory storing an executable code and a hardware processor executing the executable code to receive a plurality of training contents depicting a plurality of activities, extract training object data from the plurality of training contents including a first training object data corresponding to a first activity, extract training scene data from the plurality of training contents including a first training scene data corresponding to the first activity, determine that a probability of the first activity is maximized when the first training object data and the first training scene data both exist in a sample media content.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式