Audio-visual simulation-generating neural network system

    公开(公告)号:US11361563B2

    公开(公告)日:2022-06-14

    申请号:US17103336

    申请日:2020-11-24

    IPC分类号: G06V30/194

    摘要: Embodiments of the present invention provide a system of interconnected neural networks capable audio-visual simulation generation by interpreting and processing a first image and, utilizing a given reference image or training set, modifying the first image such that the new image possesses parameters found within the reference image or training set. The images used and generated may include video. The system includes an autoposer, an automasker, an encoder, a generator, an improver, a discriminator, styler, and at least one training set of images or video. The system can also generate training sets for use within.

    Systems and methods for discovery of related terms for social media content collection over social networks
    2.
    发明申请
    Systems and methods for discovery of related terms for social media content collection over social networks 审中-公开
    用于发现社交网络社交媒体内容收集的相关术语的系统和方法

    公开(公告)号:US20130304818A1

    公开(公告)日:2013-11-14

    申请号:US13853718

    申请日:2013-03-29

    IPC分类号: H04L29/08

    摘要: A new approach is proposed that contemplates systems and methods to discover one or more terms related to one or more query terms submitted by a user for search over a social media network, wherein the related terms discovered are trending and co-occurring with the submitted query terms over the social media network during a specific period of time. The terms related to the submitted keywords can be discovered based on based on various measurements that measure the trending characteristics of the terms in the social media content items collected over a period of time. Once the terms related to the submitted keywords have been discovered, they can be utilized to search or perform aggregated metrics and analytics on the social network together with the user-submitted query terms for content items containing all or most of the query terms and/or the related terms, wherein such content items obtained are presented as the search result to the user or subject to aggregate metrics and analytics presented to the user.

    摘要翻译: 提出了一种新方法,其考虑系统和方法来发现与通过社交媒体网络进行搜索的用户提交的一个或多个查询词相关的一个或多个术语,其中发现的相关术语与所提交的查询趋势并且共同发生 在一段特定时期内,社交媒体网络的条款。 与提交的关键词相关的术语可以基于各种度量在一段时间内收集的社交媒体内容项中的术语的趋势特征的测量来发现。 一旦与提交的关键字相关的术语已经被发现,它们可以用于在社交网络上搜索或执行聚合度量和分析,以及用户提交的查询条款,用于包含所有或大多数查询词语的内容项目和/或 相关术语,其中所获得的这样的内容项目作为搜索结果呈现给用户或受到呈现给用户的聚合度量和分析。

    AUDIO-VISUAL SIMULATION-GENERATING NEURAL NETWORK SYSTEM

    公开(公告)号:US20210158109A1

    公开(公告)日:2021-05-27

    申请号:US17103336

    申请日:2020-11-24

    IPC分类号: G06K9/66

    摘要: Embodiments of the present invention provide a system of interconnected neural networks capable audio-visual simulation generation by interpreting and processing a first image and, utilizing a given reference image or training set, modifying the first image such that the new image possesses parameters found within the reference image or training set. The images used and generated may include video. The system includes an autoposer, an automasker, an encoder, a generator, an improver, a discriminator, styler, and at least one training set of images or video. The system can also generate training sets for use within.