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. 发明申请

WO2017079362A1 CAPTION GENERATION FOR VISUAL MEDIA 审中-公开
标题翻译：字幕媒体的字幕生成
公开(公告)号：WO2017079362A1
公开(公告)日：2017-05-11
申请号：PCT/US2016/060206
申请日：2016-11-03
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： VALLIANI, Jamil , BECKER, Ryan , PRAJAPATI, Gaurang , SACHETI, Arun , CHO, Soo Hoon
IPC分类号： G06F17/30
CPC分类号： G06T11/60 , G06F3/0482 , G06F3/0484 , G06F17/241 , G06F17/248 , G06F17/30265 , G06K9/6267 , G06T2200/24
摘要： Aspects of the technology described herein automatically generate captions for visual media, such as a photograph or video. The caption can be presented to a user for adoption and/or modification. If adopted, the caption could be associated with the image and then forwarded to the user's social network, a group of users, or any individual or entity designated by a user. The caption is generated using data from the image in combination with signal data received from a mobile device on which the visual media is present. The data from the image could be gathered via object identification performed on the image. The signal data can be used to determine a context for the image. The signal data can also help identify other events that are associated with the image, for example, that the user is on vacation. The caption is built using information from both the picture and context.
摘要翻译：这里描述的技术的各方面自动生成诸如照片或视频之类的视觉媒体的标题。该标题可以呈现给用户以供采用和/或修改。如果采用，标题可以与图像相关联，然后转发给用户的社交网络，一组用户或用户指定的任何个人或实体。使用来自图像的数据结合从存在可视媒体的移动设备接收的信号数据生成字幕。来自图像的数据可以通过在图像上执行的对象识别来收集。信号数据可以用来确定图像的上下文。信号数据还可以帮助识别与图像相关的其他事件，例如用户正在度假。标题是使用来自图片和上下文的信息构建的。

2. 发明申请

WO2023059382A1 IN-CONTEXT VISUAL SEARCH 审中-公开
公开(公告)号：WO2023059382A1
公开(公告)日：2023-04-13
申请号：PCT/US2022/038251
申请日：2022-07-26
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC.
发明人： RAY, Nicholas Fredrick , CURTIS, Adam Jeffrey , DEVRIES, Jeffrey Roger , ISMAILCIUC, Cheyenne , ABRAHAM, Niveah Tefillah , IOANNIDES, Nektarios , SACHETI, Arun , VEMULURU, Avinash
IPC分类号： G06F16/9538 , G06F16/957 , G06F16/9577
摘要： The present disclosure relates to systems and methods for providing a visual search within a browser. The systems and methods allow users to trigger a visual search from the browser within the user's browsing context. The users may trigger a visual search by hovering over an image and selecting a visual search icon or selecting a visual search option within a context menu. Selecting the visual searches may cause a sidebar to open with visual search results or a flyout to display with visual search results.

3. 发明申请

WO2017062220A1 GENERATING IMAGE TAGS 审中-公开
标题翻译：生成图像标签
公开(公告)号：WO2017062220A1
公开(公告)日：2017-04-13
申请号：PCT/US2016/053859
申请日：2016-09-27
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： YUEN, Aaron Chun Win , MICHELIS, Alexandre B.R , SACHETI, Arun , HASHAM, Karim A. , SUN, Yanfeng
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/30253 , G06F17/30265 , G06F17/30268 , G06F17/30867
摘要： The technology described herein provides an efficient mechanism for generating image tags. Image data from a plurality of sources may be analyzed to identify relevant text items from the aggregated data. The relevant text items may be keywords describing a subject of an image, an entity of an image, a location of an image, or the like. From the aggregated image data, one or more image tags may be generated and stored as an offline dataset with an image identifier. Upon detecting a prompt such as a user issuing a search query for an image, the image identifier is used to perform a look up of the image and associated image tags to be provided.
摘要翻译：本文描述的技术提供了用于生成图像标签的有效机制。可以分析来自多个源的图像数据以从聚合数据识别相关文本项。相关文本项可以是描述图像的主题，图像的实体，图像的位置等的关键字。从聚合的图像数据中，可以生成一个或多个图像标签并将其存储为具有图像标识符的脱机数据集。当检测到诸如用户对图像发出搜索查询的提示时，图像标识符用于执行要提供的图像和相关联的图像标签的查找。

4. 发明申请

WO2020018210A1 VISUAL INTENT TRIGGERING FOR VISUAL SEARCH 审中-公开
公开(公告)号：WO2020018210A1
公开(公告)日：2020-01-23
申请号：PCT/US2019/037582
申请日：2019-06-18
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： CHEN, Xi , HU, Houdong , HUANG, Li , HUANG, Jiapei , SACHETI, Arun , YANG, Linjun , XIA, Rui , LEE, Kuang-Huei , MERCHANT, Meenaz , CULATANA, Sean Chang
IPC分类号： G06F16/50 , G06F16/35 , G06F16/583
摘要： Representative embodiments disclose mechanisms to perform visual intent classification or visual intent detection or both on an image. Visual intent classification utilizes a trained machine learning model that classifies subjects in the image according to a classification taxonomy. The visual intent classification can be used as a pre-triggering mechanism to initiate further action in order to substantially save processing time. Example further actions include user scenarios, query formulation, user experience enhancement, and so forth. Visual intent detection utilizes a trained machine learning model to identify subjects in an image, place a bounding box around the image, and classify the subject according to the taxonomy. The trained machine learning model utilizes multiple feature detectors, multi-layer predictions, multilabel classifiers, and bounding box regression.

5. 发明申请

WO2017040224A1 RECOMMENDING A CONTENT CURATOR 审中-公开
标题翻译：推荐一款内置计算机
公开(公告)号：WO2017040224A1
公开(公告)日：2017-03-09
申请号：PCT/US2016/048802
申请日：2016-08-26
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： SACHETI, Arun , SUN, Yanfeng , YUEN, Aaron Chun Win , GOVINDARAJEN, Parthasarathy , WU, Kun , CHO, Soohoon , PRADHAN, Malik Mehdi , MICHELIS, Alexandre , VAIDYA, Gautam Vishwas , HASHAM, Karim Amin , VEMULURU, Avinash
IPC分类号： G06F17/30
CPC分类号： G06F17/3053 , G06F17/30038 , G06F17/30554 , G06F17/30867 , G06N99/005
摘要： The technology described herein provides an efficient mechanism for quickly analyzing huge amounts of media content to find media content (hereafter "content" or "media content") that is relevant to a user. The technology analyzes features of a curator to classify curators by interest and/or find curators with similar content recommendations. The curator data can be used to make curator recommendations to users based on the user's interests. The technology described herein collects curator data from multiple content sites and analyzes the data to identify curators that recommend similar content on different content sites.
摘要翻译：本文描述的技术提供了一种用于快速分析大量媒体内容以找到与用户相关的媒体内容（以下称为“内容”或“媒体内容”）的有效机制。该技术分析策展人的特征，以便按照兴趣对策展人进行分类和/或找到具有类似内容建议的策展人。策展人数据可以根据用户的兴趣使用策展人推荐给用户。本文描述的技术从多个内容站点收集策展人数据，并分析数据以识别在不同内容网站上推荐类似内容的策展人。

6. 发明申请

WO2020197636A1 ENCODER USING MACHINE-TRAINED TERM FREQUENCY WEIGHTING FACTORS THAT PRODUCES A DENSE EMBEDDING VECTOR 审中-公开
公开(公告)号：WO2020197636A1
公开(公告)日：2020-10-01
申请号：PCT/US2020/016305
申请日：2020-02-03
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： WANG, Yan , WU, Ye , HU, Houdong , ULABALA, Surendra , THAKKAR, Vishal , SACHETI, Arun
IPC分类号： G06F16/33 , G06N3/04
摘要： A computer-implemented technique is described herein for generating a dense embedding vector that provides a distribution representation of input text. In one implementation, the technique includes: generating an input term -frequency (TF) vector of dimension g that includes frequency information relating to frequency of occurrence of terms in an instance of input text; using a TF-modifying to modify the term-specific frequency information in the input TF vector by respective machine-trained weighting factors, to produce an intermediate vector of dimension g , using a projection component to project the intermediate vector of dimension g into an embedding vector of dimension k , where k is less than g . Both the TF-modifying component and the projection component can use respective machine-trained neural networks. An application component can perform any of a retrieval-based function, a recognition-based function, a recommendation- based function, a classification-based function, etc. based on the embedding vector.

7. 发明申请

WO2018089222A1 RESPONSIVE CUSTOMIZED DIGITAL STICKERS 审中-公开
标题翻译：响应式个性化数字贴纸
公开(公告)号：WO2018089222A1
公开(公告)日：2018-05-17
申请号：PCT/US2017/059140
申请日：2017-10-31
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： DE ABREU RODRIGUEZ, Juan Carlos , GREATHOUSE, Wallace E. , ZHANG, Li , CHO, Soohoon , KAO, Shannon , LEUNG, Vincent , SACHETI, Arun
IPC分类号： G06Q50/00 , H04M1/725 , G06F3/0488 , G06F17/30
CPC分类号： G06T11/60 , G06F16/532 , G06Q50/01 , H04M1/72555
摘要： Data regarding a base digital image and a request to generate one or more customized digital stickers for the base digital image can be received. In response to the received request, a customized digital sticker can be generated for the base digital image using results of analysis of the data regarding the base digital image, with the customized sticker including multiple visual features. The generating can include generating a customized digital sticker using a set of sticker generation rules, with the layout of multiple visual features of the digital sticker being dictated by the sticker generation rules, and with the generating of the sticker including combining the multiple visual features in the digital sticker. The digital sticker can be overlaid on the base digital image to produce a composite digital image.
摘要翻译：可以接收关于基本数字图像的数据和为基本数字图像生成一个或多个定制数字标签的请求。响应于接收到的请求，可以使用关于基本数字图像的数据的分析结果来为基本数字图像生成定制数字贴纸，其中定制贴纸包括多个视觉特征。生成可以包括使用一组标签生成规则来生成定制的数字标签，其中数字标签的多个视觉特征的布局由标签生成规则支配，并且生成标签包括将多个视觉特征组合数字贴纸。数字贴纸可以叠加在基本数字图像上以生成复合数字图像。

8. 发明申请

WO2016044235A1 CONTENT INTERFACE LAYOUT CONSTRUCTION 审中-公开
标题翻译：内容接口布局结构
公开(公告)号：WO2016044235A1
公开(公告)日：2016-03-24
申请号：PCT/US2015/050132
申请日：2015-09-15
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： SANTHANAM, Deepak , SACHETI, Arun , GUO, Yandong , GOVINDARAJEN, Parthasarathy , PARAKHIN, Mikhail Valeryevich
IPC分类号： G06F17/30
CPC分类号： G06F17/30867 , G06F3/0482 , G06F3/04842 , G06F3/0485 , G06F17/30528 , G06F17/3053 , G06F17/30991
摘要： One or more techniques and/or systems are provided for constructing a content interface layout. For example a search query may be received from a user of a device. A content interest context for the user may be identified (e.g., a time of day, a season, a user location, a user social network post about planting a garden, device type of the user, etc.). Content interfaces (e.g., a gardening image collection, a tomato planting instructional app, a soil related topic search suggestion, etc.) may be populated within content interface slots of a search results canvas for the search query based upon user engagement metrics and the content interest context. In this way, content interfaces, comprising supplemental content, may be assigned to content interface slots so that such content interfaces have a high probability of being relevant to and/or engaged by the user.
摘要翻译：提供了一个或多个技术和/或系统来构建内容接口布局。例如，可以从设备的用户接收搜索查询。可以识别用户的内容兴趣上下文（例如，一天中的时间，季节，用户位置，关于种植花园的用户社交网络，用户的设备类型等）。可以基于用户参与度量和内容，在搜索结果画布的内容接口槽内填充内容界面（例如，园艺图像集合，番茄种植教学应用程序，土壤相关主题搜索建议等）兴趣上下文。以这种方式，可以将包括补充内容的内容接口分配给内容接口时隙，使得这些内容接口具有与用户相关和/或接合的高概率。

9. 发明申请

WO2021045822A1 INTERACTIVE VISUAL SEARCH ENGINE 审中-公开
公开(公告)号：WO2021045822A1
公开(公告)日：2021-03-11
申请号：PCT/US2020/038005
申请日：2020-06-17
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： HUANG, Li , HU, Houdong , MERCHANT, Meenaz , SACHETI, Arun
IPC分类号： G06F16/58 , G06F16/332 , G06F40/35
摘要： A visual search engine is described herein. The visual search engine is configured to return information to a client computing device based upon a multimodal query received from the client computing device (wherein the multimodal query comprises an image and text). The visual search engine is further configured to interact with a user of the client computing device to disambiguate information retrieval intent of the user.

10. 发明申请

WO2020236310A1 GENERATING AND APPLYING AN OBJECT-LEVEL RELATIONAL INDEX FOR IMAGES 审中-公开
公开(公告)号：WO2020236310A1
公开(公告)日：2020-11-26
申请号：PCT/US2020/025097
申请日：2020-03-27
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： WU, Kun , SHEN, Yiran , HU, Houdong , SREEPADA, Soudamini , SACHETI, Arun , GUPTA, Mithun Das , GANDHI, Rushabh Rajesh , KUMAR, Sudhir
IPC分类号： G06F16/51 , G06F16/583 , G06F16/901
摘要： A computer-implemented technique is described herein for using a machine-trained model to identify individual objects within images. The technique then creates a relational index for the identified objects. That is, each index entry in the relational index is associated with a given object, and includes a set of attributes pertaining to the given object. One such attribute identifies at least one latent semantic vector associated with the given object. Each attribute provides a way of linking the given object to one or more other objects in the relational index. In one application of this technique, a user may submit a query that specifies a query object. The technique consults the relational index to find one or more objects that are related to the query object. In some cases, the query object and each of the other objects have a complementary relationship.

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