中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.013 seconds)

    Video analysis using convolutional networks
    3.
    发明授权
    Video analysis using convolutional networks 有权

    公开(公告)号：US10706350B1

    公开(公告)日：2020-07-07

    申请号：US16101356

    申请日：2018-08-10

    Applicant: Facebook, Inc.

    Inventor： Du Le Hong Tran ,  Benjamin Ray ,  Balmanohar Paluri

    IPC: G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G06K9/62

    Abstract: In one embodiment, a method includes, by a computing device, receiving a plurality of inputs for a convolution layer of a convolutional neural network, the convolution layer having one or more input channels and one or more output channels, wherein the inputs are received via the input channels, generating, by convolving the inputs with one or more two-dimensional filters, a plurality of intermediate values, and generating, by convolving the intermediate values with one or more one-dimensional filters, a plurality of outputs, wherein the one-dimensional filters receive the intermediate values from the two-dimensional filters via intermediate channels. The method may provide the outputs to a subsequent layer of the convolutional neural network via the output channels. Each of the two dimensions of the two-dimensional filter may correspond to a spatial dimension, and the one dimension of the one-dimensional filter may correspond to a temporal dimension.

    SYSTEMS AND METHODS FOR INCREMENTAL MEDIA PROCESSING BASED ON UTILIZING CLIENT-SIDE COMPUTATION
    4.
    发明申请
    SYSTEMS AND METHODS FOR INCREMENTAL MEDIA PROCESSING BASED ON UTILIZING CLIENT-SIDE COMPUTATION 审中-公开

    公开(公告)号：US20170372138A1

    公开(公告)日：2017-12-28

    申请号：US15192804

    申请日：2016-06-24

    Applicant: Facebook, Inc.

    Inventor： Karthik Subbian ,  Benjamin Ray

    IPC: G06K9/00 ,  G11B27/10

    CPC classification number: G06K9/00664 ,  G06Q50/01 ,  G11B27/10

    Abstract: Systems, methods, and non-transitory computer-readable media can identify a media content item for which media processing is to be performed. State information associated with the media content item can be acquired. At least some of the media processing can be enabled, based on the state information, to be performed client-side with respect to the media content item. The state information can indicate a next processing step of the at least some of the media processing that is to be performed. The state information can be updated based on the at least some of the media processing performed client-side.

    Unsupervised video segmentation
    5.
    发明授权
    Unsupervised video segmentation 有权

    公开(公告)号：US10402986B2

    公开(公告)日：2019-09-03

    申请号：US15849341

    申请日：2017-12-20

    Applicant: Facebook, Inc.

    Inventor： Benjamin Ray ,  Anurag Ranjan

    IPC: G06T7/215 ,  G06T7/246 ,  G06T7/33 ,  G06N20/00

    Abstract: In one embodiment, a method includes a computing system accessing a first training data comprising a first image and a second image and an associated optical flow estimation. The system may input (1) the first image into a first machine-learning model configured to generate a first output and (2) the optical flow estimation into a second machine-learning model configured to generate a second output. The first output of the first machine-learning model is associated with first image segments of a predetermined number, and the second output of the second machine-learning model is associated with transformations of the predetermined number. The first output, the transformations, and the first image are configured to generate an estimated image. The system trains the first machine-learning model and the second machine-learning model based on at least a comparison of the estimated image and the second image.

    Unsupervised Video Segmentation
    6.
    发明申请
    Unsupervised Video Segmentation 审中-公开

    公开(公告)号：US20190188863A1

    公开(公告)日：2019-06-20

    申请号：US15849341

    申请日：2017-12-20

    Applicant: Facebook, Inc.

    Inventor： Benjamin Ray ,  Anurag Ranjan

    IPC: G06T7/215 ,  G06T7/246 ,  G06F15/18 ,  G06T7/33

    CPC classification number: G06T7/215 ,  G06K9/00 ,  G06N20/00 ,  G06T7/251 ,  G06T7/344 ,  G06T2207/10016 ,  G06T2207/20081 ,  G06T2207/20084

    Abstract: In one embodiment, a method includes a computing system accessing a first training data comprising a first image and a second image and an associated optical flow estimation. The system may input (1) the first image into a first machine-learning model configured to generate a first output and (2) the optical flow estimation into a second machine-learning model configured to generate a second output. The first output of the first machine-learning model is associated with first image segments of a predetermined number, and the second output of the second machine-learning model is associated with transformations of the predetermined number. The first output, the transformations, and the first image are configured to generate an estimated image. The system trains the first machine-learning model and the second machine-learning model based on at least a comparison of the estimated image and the second image.

Patent Agency Ranking