知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

1181 条记录 (耗时 0.027 秒)

    Synchronizing independent media and data streams using media stream synchronization points
    42.
    发明公开
    Synchronizing independent media and data streams using media stream synchronization points 审中-公开

    公开(公告)号：US20240155019A1

    公开(公告)日：2024-05-09

    申请号：US18413448

    申请日：2024-01-16

    申请人： Akamai Technologies, Inc.

    发明人： Michael M. Archer ,  Michael Archer

    IPC分类号： H04L65/75 ,  H04L65/612 ,  H04L65/80

    CPC分类号： H04L65/764 ,  H04L65/612 ,  H04L65/80

    摘要： A messaging channel is embedded directly into a media stream. Messages delivered via the embedded messaging channel are extracted at a client media player. In lieu of embedding the message data in the media stream, a coordination index is injected, and the message data is sent separately and merged into the media stream downstream (at the media player) based on the index. In one example embodiment, multiple data streams (each potentially with different content intended for a particular “type” or class of user) are transmitted alongside the video stream in which the coordination index has been injected into a video frame. Based on a user's service level, a particular one of the multiple data streams is released when the sequence number appears in the video frame, and the data in that stream is associated with the media.

    MASKED MODEL TRAINING OF A PREDICTION NETWORK
    48.
    发明公开
    MASKED MODEL TRAINING OF A PREDICTION NETWORK 审中-公开

    公开(公告)号：US20240137620A1

    公开(公告)日：2024-04-25

    申请号：US18402643

    申请日：2024-01-02

    申请人： HULU, LLC

    发明人： Pengyu Zhao ,  Chunxu Xu ,  Xianghui Mao ,  Xiaohui Xie

    IPC分类号： H04N21/482 ,  G06N3/045 ,  G06N3/084 ,  H04L65/612

    CPC分类号： H04N21/4826 ,  G06N3/045 ,  G06N3/084 ,  H04L65/612

    摘要： In some embodiments, a method receives a first sequence of inputs for processing via a sub-model of a plurality of sub-model. The plurality of sub-models are part of a main model. An input in the sequence of inputs is masked with a masked value to generate a second sequence of inputs. The method processes the second sequence of inputs using the sub-model to generate a sequence of features that correspond to the second sequence of inputs and processes the sequence of features to generate a first output. The first output is processed to generate a second output of the main model. The sub-model is trained based on a feature in the sequence of features that corresponds to the masked input and the second output.

    Multimodal content recognition and contextual advertising and content delivery
    50.
    发明授权
    Multimodal content recognition and contextual advertising and content delivery 有权

    公开(公告)号：US11962634B2

    公开(公告)日：2024-04-16

    申请号：US17556358

    申请日：2021-12-20

    申请人： eBay Inc.

    发明人： Neelakantan Sundaresan

    IPC分类号： H04L67/01 ,  G06F7/76 ,  G06F15/16 ,  H04L15/16 ,  H04L65/00 ,  H04L65/1089 ,  H04L65/612

    CPC分类号： H04L67/01 ,  H04L65/00 ,  H04L65/1089 ,  H04L65/612

    摘要： The present disclosure is directed to providing supplemental content to one or more client devices requesting multimedia content. The supplemental content may be determined or selected based on the availability of one or more device channels, such as a display, speakers, or other component of the one or more client devices capable of providing an output. The supplemental content may also be selected based on one or more characteristics of the requested multimedia content, such as a genre, subject matter, or duration. Furthermore, the supplemental content may be determined or selected based on the portions of the requested multimedia content that are the most prominent or significant, such as any audio content, any video content, and/or any textual content. The supplemental content may be provided to the one or more client devices such that it is displayed before, during, or after the display of the requested multimedia content.