-
公开(公告)号：US09807473B2
公开(公告)日：2017-10-31
申请号：US14946988
申请日：2015-11-20
Applicant: Microsoft Technology Licensing, LLC
IPC: H04N5/445 , H04N21/8405 , G06F17/27 , G06K9/00 , G06N3/08
CPC classification number: H04N21/8405 , G06F17/274 , G06F17/2785 , G06K9/00718 , G06K9/6273 , G06N3/08 , H04N21/26603
Abstract: Video description generation using neural network training based on relevance and coherence is described. In some examples, long short-term memory with visual-semantic embedding (LSTM-E) can maximize the probability of generating the next word given previous words and visual content and can create a visual-semantic embedding space for enforcing the relationship between the semantics of an entire sentence and visual content. LSTM-E can include a 2-D and/or 3-D deep convolutional neural networks for learning powerful video representation, a deep recurrent neural network for generating sentences, and a joint embedding model for exploring the relationships between visual content and sentence semantics.
-
公开(公告)号：US20170150235A1
公开(公告)日：2017-05-25
申请号：US14946988
申请日：2015-11-20
Applicant: Microsoft Technology Licensing, LLC
IPC: H04N21/8405 , G06K9/00 , G06N3/08 , G06F17/27
CPC classification number: H04N21/8405 , G06F17/274 , G06F17/2785 , G06K9/00718 , G06K9/6273 , G06N3/08 , H04N21/26603
Abstract: Video description generation using neural network training based on relevance and coherence is described. In some examples, long short-term memory with visual-semantic embedding (LSTM-E) can maximize the probability of generating the next word given previous words and visual content and can create a visual-semantic embedding space for enforcing the relationship between the semantics of an entire sentence and visual content. LSTM-E can include a 2-D and/or 3-D deep convolutional neural networks for learning powerful video representation, a deep recurrent neural network for generating sentences, and a joint embedding model for exploring the relationships between visual content and sentence semantics.
-
公开(公告)号：US20170139954A1
公开(公告)日：2017-05-18
申请号：US15323247
申请日：2014-07-04
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Tao Mei , Yan-Feng Sun , Yong Rui , Chun-Che Wu
IPC: G06F17/30
CPC classification number: G06F16/50 , G06F16/532 , G06F16/58 , G06F16/90324 , G06F16/9038 , G06F16/9535
Abstract: Techniques and constructs to facilitate suggestion of image-based search queries can provide personalized trending image search queries. The constructs may enable identification of trending image searches and further personalize those trending image search queries for an identified user based on information about on the user's search history and the search histories of other users. The constructs also may select a representative image for display to the user, such that selection of the representative image will execute the search query. The representative image may be selected from a plurality of candidate images based on its burstiness.
-
公开(公告)号：US20160275067A1
公开(公告)日：2016-09-22
申请号：US14664365
申请日：2015-03-20
Applicant: Microsoft Technology Licensing, LLC
Inventor： Tao Mei , Yong Rui , Shipeng Li
Abstract: A layout generator generates a layout for communications media content based on an identified domain (e.g., topic). A communications media content analyzer identifies a domain associated with communications media content. A domain-based layout guide selector receives the identified domain from the communications media content analyzer and selects a domain-based layout guide based on the identified domain. The domain-based layout guide is selected from a set of domain-based layout guides stored in memory accessible by the one or more processors. The set of domain-based layout guides is associated with multiple domains. A communications media content layout generator receives the selected domain-based layout guide from the domain-based layout guide selector and generates a communications media content layout incorporating at least a subset of the communications media content. The communications media content layout complies with the selected domain-based layout guide.
Abstract translation: 布局生成器基于识别的域（例如，主题）生成用于通信媒体内容的布局。 通信媒体内容分析器识别与通信媒体内容相关联的域。 基于域的布局指南选择器从通信媒体内容分析器接收所识别的域，并基于所识别的域选择基于域的布局指南。 基于域的布局指南是从存储在一个或多个处理器可访问的存储器中的一组基于域的布局指南中选择的。 一组基于域的布局指南与多个域相关联。 通信媒体内容布局生成器从基于域的布局指南选择器接收所选择的基于域的布局指南，并且生成包含通信媒体内容的至少一个子集的通信媒体内容布局。 通信媒体内容布局符合所选的基于域的布局指南。
-
公开(公告)号：US20180060724A1
公开(公告)日：2018-03-01
申请号：US15247673
申请日：2016-08-25
Applicant: Microsoft Technology Licensing, LLC
Inventor： Changhu Wang , Yong Rui , Tao Wei
CPC classification number: G06N3/082 , G06N3/0454
Abstract: This disclosure describes techniques and architectures to morph well-trained networks to other related applications or modified networks with relatively little retraining. For example, a well-trained neural network (e.g., parent network) may be morphed to a new neural network (e.g., child network) so that the new neural network function may be preserved. After morphing a parent network, the child network may inherit the knowledge from its parent network and also may have a potential to continue growing into a more powerful network. Such morphing and growing may occur with a relatively short training time.
-
Patent Agency Ranking
公开(公告)号：US09754188B2
公开(公告)日：2017-09-05
申请号：US14522194
申请日：2014-10-23
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Tao Mei , Jianlong Fu , Kuiyuan Yang , Yong Rui
CPC classification number: G06K9/6256 , G06F17/30247 , G06F17/30256 , G06F17/3028 , G06K9/627
Abstract: Techniques and constructs to facilitate automatic tagging can provide improvements in image storage and searching. The constructs may enable training a deep network using tagged source images and target images. The constructs may also train a top layer of the deep network using a personal photo ontology. The constructs also may select one or more concepts from the ontology for tagging personal digital images.
-
公开(公告)号：US20170109584A1
公开(公告)日：2017-04-20
申请号：US14887629
申请日：2015-10-20
Applicant: Microsoft Technology Licensing, LLC
IPC: G06K9/00 , G11B27/30 , G11B27/031
CPC classification number: G06K9/00718 , G06K9/00751 , G11B27/031 , G11B27/3081 , H04N21/45457 , H04N21/4666 , H04N21/8549
Abstract: Video highlight detection using pairwise deep ranking neural network training is described. In some examples, highlights in a video are discovered, then used for generating summarization of videos, such as first-person videos. A pairwise deep ranking model is employed to learn the relationship between previously identified highlight and non-highlight video segments. This relationship is encapsulated in a neural network. An example two stream process generates highlight scores for each segment of a user's video. The obtained highlight scores are used to summarize highlights of the user's video.
-
公开(公告)号：US20170055075A1
公开(公告)日：2017-02-23
申请号：US15345465
申请日：2016-11-07
Applicant: Microsoft Technology Licensing, LLC
Inventor： Desney S. Tan , Daniel Morris , Andrew D. Wilson , Yong Rui , Nikunj Raghuvanshi , Jeannette M. Wing
CPC classification number: H04R29/00 , H04M1/72558 , H04R3/04 , H04R5/04 , H04R27/00 , H04R2227/005 , H04S7/301 , H04W4/023
Abstract: Technologies pertaining to calibration of filters of an audio system are described herein. A mobile computing device is configured to compute values for respective filters, such as equalizer filters, and transmit the values to a receiver device in the audio system. The receiver device causes audio to be emitted from a speaker based upon the values for the filters.
Abstract translation: 本文描述了关于音频系统的滤波器的校准的技术。 移动计算设备被配置为计算各个滤波器的值，例如均衡器滤波器，并且将值发送到音频系统中的接收机设备。 接收机设备基于滤波器的值使扬声器发出音频。
-
公开(公告)号：US09338440B2
公开(公告)日：2016-05-10
申请号：US13919933
申请日：2013-06-17
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
CPC classification number: H04N13/282 , G06F3/00 , G06T19/006 , H04N5/23216 , H04N5/23293 , H04N13/221 , H04N13/296
Abstract: A method of acquiring a set of images useable to 3D model a physical object includes imaging the physical object with a camera, and displaying with the camera a current view of the physical object as imaged by the camera from a current perspective. The method further includes displaying with the camera a visual cue overlaying the current view and indicating perspectives from which the physical object is to be imaged to acquire the set of images.
Abstract translation: 获取可用于对物理对象进行3D建模的一组图像的方法包括用相机对物理对象进行成像，并且从当前的角度通过相机显示物理对象的当前视图。 该方法还包括用相机显示覆盖当前视图的视觉提示，并且指示要从其中成像物理对象的视角以获取该组图像。
-
公开(公告)号：US10341857B2
公开(公告)日：2019-07-02
申请号：US15879137
申请日：2018-01-24
Applicant: Microsoft Technology Licensing, LLC
Inventor： Yong Rui , Daniel Morris , Andrew D. Wilson , Nikunj Raghuvanshi , Desney S. Tan , Jeannette M. Wing
Abstract: A privacy preserving sensor apparatus is described herein. The privacy preserving sensor apparatus includes a microphone that is configured to output a signal that is indicative of audio in an environment. The privacy preserving sensor apparatus further includes feature extraction circuitry integrated in the apparatus with the microphone, the feature extraction circuitry configured to extract features from the signal output by the microphone that are usable to detect occurrence of an event in the environment, wherein the signal output by the microphone is unable to be reconstructed based solely upon the features.
-
-
-
-
-
-
-
-
-
Search Results
15
records
(took 0.02 seconds)
