中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

36 records (took 0.02 seconds)

    Update basis for updating digital content in a digital medium environment
    31.
    发明授权
    Update basis for updating digital content in a digital medium environment 有权

    公开(公告)号：US10657118B2

    公开(公告)日：2020-05-19

    申请号：US15726125

    申请日：2017-10-05

    Applicant: Adobe Inc.

    Inventor： Gavin Stuart Peter Miller ,  Kevin Gary Smith ,  Kent Andrew Edmonds ,  Govind P. Balakrishnan

    IPC: G06F15/16 ,  G06F16/23 ,  H04W4/60 ,  G06F16/48 ,  G06F16/958 ,  H04L29/08 ,  H04L29/06

    Abstract: An update basis for updating digital content in a digital medium environment is described. The digital content is updated by incorporating new digital content components from a service provider system, such as a stock content service, to keep the digital content from seeming stale to client device users. The service provider system controls provision of digital content components according to an update basis described in a component request. In part, component requests ask that the service provider system provide digital content components for incorporation with digital content. Component requests also describe a timing basis with which digital content components are to be provided as updates. By way of example, the timing basis may correspond to a time interval (e.g., daily, weekly, monthly, seasonally, times of day, and so on), receiving user input in relation to the digital content (e.g., a navigation input to a web page), and so forth.

    Convolutional neural network joint training
    33.
    发明授权
    Convolutional neural network joint training 有权

    公开(公告)号：US10467529B2

    公开(公告)日：2019-11-05

    申请号：US15177121

    申请日：2016-06-08

    Applicant: Adobe Inc.

    Inventor： Zhe Lin ,  Yufei Wang ,  Radomir Mech ,  Xiaohui Shen ,  Gavin Stuart Peter Miller

    IPC: G06N3/08 ,  G06N3/04

    Abstract: In embodiments of convolutional neural network joint training, a computing system memory maintains different data batches of multiple digital image items, where the digital image items of the different data batches have some common features. A convolutional neural network (CNN) receives input of the digital image items of the different data batches, and classifier layers of the CNN are trained to recognize the common features in the digital image items of the different data batches. The recognized common features are input to fully-connected layers of the CNN that distinguish between the recognized common features of the digital image items of the different data batches. A scoring difference is determined between item pairs of the digital image items in a particular one of the different data batches. A piecewise ranking loss algorithm maintains the scoring difference between the item pairs, and the scoring difference is used to train CNN regression functions.

    Photorealistic augmented reality system
    34.
    发明授权
    Photorealistic augmented reality system 有权

    公开(公告)号：US10403045B2

    公开(公告)日：2019-09-03

    申请号：US15675045

    申请日：2017-08-11

    Applicant: Adobe Inc.

    Inventor： Stefano Koenig Corazza ,  Gavin Stuart Peter Miller

    IPC: G06T15/50 ,  G06T15/60 ,  G06T19/00

    Abstract: A digital medium environment includes at least one computing device (e.g., a user's mobile device) in an environment. Systems and techniques are described for presenting a photorealistic augmented reality experience in real time on the computing device. A lighting representation of the environment is obtained from a partial view of the environment, such as from an image of the environment, and used to render a 3D asset (e.g., graphics of a synthetic object). The 3D asset is inserted into the environment by compositing the rendered 3D asset with the image of the environment accounting for occlusion and based on the lighting representation to form a composite image. Photorealistic processing is applied to the composite image by adding lighting for the rendered 3D asset to a portion of the background of the composite image. Consequently, the inserted graphic is indistinguishable from the real-world scene.

Patent Agency Ranking