知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

5 records (took 0.019 seconds)

    FACE SYNCING IN DISTRIBUTED COMPUTING ENVIRONMENT
    1.
    发明申请
    FACE SYNCING IN DISTRIBUTED COMPUTING ENVIRONMENT 审中-公开

    公开(公告)号：US20190340801A1

    公开(公告)日：2019-11-07

    申请号：US16511820

    申请日：2019-07-15

    Applicant: Apple Inc.

    Inventor： Gavin B. Thomson ,  Eric Circlaeys ,  Paul M. Bombach ,  Tony F. Kinnis ,  Baskaran Subramaniam

    IPC: G06T11/60 ,  H04L29/08 ,  G06K9/00

    Abstract: Embodiments are disclosed for face syncing in a distributed computing environment. In an embodiment, a method comprises: obtaining, by a processor, media assets that include faces of individuals; detecting, by the processor of a mobile device, the faces on the media assets; generating, by the processor, faceprints for the detected faces; clustering, by the processor, the faceprints into clusters; generating, by the processor, a face crop image for each cluster; and sending, by the processor, the face crop images to a network-based, distributed syncing service.

    Auto-reframing and multi-cam functions of video editing application
    2.
    发明申请
    Auto-reframing and multi-cam functions of video editing application 有权

    公开(公告)号：US20240378850A1

    公开(公告)日：2024-11-14

    申请号：US18314095

    申请日：2023-05-08

    Applicant: Apple Inc.

    Inventor： Paul M. Bombach ,  James C. Arndt ,  David N. Chen ,  Todd E. Kramer ,  Shaun M. Poole ,  Rupamay Saha ,  Eugene M. Walden

    IPC: G06V10/70 ,  H04N7/01

    Abstract: In one or more embodiments, a computing device is configured to modify an original video by applying a machine learning model. The computing device obtains multiple training data sets, with each particular training data set including an original video and a corresponding modified video. One or more frames from the original video are cropped to generate corresponding frames in the corresponding modified video. The computing device trains a machine learning model, using the training data sets, to generate modified videos from original videos such that one or more frames in the original videos are modified to generate corresponding frames in respective modified videos. Once the machine learning model is trained, the computing device obtains a target original video and applies the trained machine learning model to the target original video to generate a target modified video.

Patent Agency Ranking