中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

43 records (took 0.023 seconds)

    Systems and methods for determining optical flow
    1.
    发明授权
    Systems and methods for determining optical flow 有权

    公开(公告)号：US10181195B2

    公开(公告)日：2019-01-15

    申请号：US14980786

    申请日：2015-12-28

    Applicant: Facebook, Inc.

    Inventor： Balamanohar Paluri

    IPC: G06K9/00 ,  G06T7/20 ,  G06K9/62

    Abstract: Systems, methods, and non-transitory computer-readable media can obtain a first video frame and a second video frame. The first video frame can be processed using a convolutional neural network to output a first set of feature maps. The second video frame can be processed using the convolutional neural network to output a second set of feature maps. The first set of feature maps and the second set of feature maps can be processed using a spatial matching layer of the convolutional neural network to determine an optical flow for at least one pixel.

    SYSTEMS AND METHODS FOR DETERMINING OPTICAL FLOW
    4.
    发明申请
    SYSTEMS AND METHODS FOR DETERMINING OPTICAL FLOW 审中-公开

    公开(公告)号：US20170186176A1

    公开(公告)日：2017-06-29

    申请号：US14980786

    申请日：2015-12-28

    Applicant: Facebook, Inc.

    Inventor： Balamanohar Paluri

    IPC: G06T7/20 ,  G06K9/62

    CPC classification number: G06K9/4628 ,  G06K9/6274 ,  G06T7/246 ,  G06T2207/10016 ,  G06T2207/20084

    Abstract: Systems, methods, and non-transitory computer-readable media can obtain a first video frame and a second video frame. The first video frame can be processed using a convolutional neural network to output a first set of feature maps. The second video frame can be processed using the convolutional neural network to output a second set of feature maps. The first set of feature maps and the second set of feature maps can be processed using a spatial matching layer of the convolutional neural network to determine an optical flow for at least one pixel.

    Systems and methods for identifying users in media content based on poselets and neural networks
    5.
    发明授权
    Systems and methods for identifying users in media content based on poselets and neural networks 有权
    基于姿态和神经网络识别媒体内容用户的系统和方法

    公开(公告)号：US09514390B2

    公开(公告)日：2016-12-06

    申请号：US14573366

    申请日：2014-12-17

    Applicant: Facebook, Inc.

    Inventor： Lubomir Bourdev ,  Ning Zhang ,  Balamanohar Paluri ,  Yaniv Taigman ,  Robert D. Fergus

    IPC: G06K9/00 ,  G06K9/66 ,  G06K9/62

    CPC classification number: G06K9/00362 ,  G06K9/00335 ,  G06K9/6215 ,  G06K9/6271 ,  G06K9/66 ,  G06N3/08

    Abstract: Systems, methods, and non-transitory computer-readable media can receive a first image including a representation of a first user. A second image including a representation of a second user can be received. A first set of poselets associated with the first user can be detected in the first image. A second set of poselets associated with the second user can be detected in the second image. The first image including the first set of poselets can be inputted into a first instance of a neural network to generate a first multi-dimensional vector. The second image including the second set of poselets can be inputted into a second instance of the neural network to generate a second multi-dimensional vector. A first distance metric between the first multi-dimensional vector and the second multi-dimensional vector can be determined.

    Abstract translation: 系统，方法和非暂时计算机可读介质可以接收包括第一用户的表示的第一图像。 可以接收包括第二用户的表示的第二图像。 可以在第一图像中检测与第一用户相关联的第一组小图。 可以在第二图像中检测与第二用户相关联的第二组小手枪。 可以将包括第一组姿态的第一图像输入到神经网络的第一实例以生成第一多维向量。 可以将包括第二组姿态的第二图像输入到神经网络的第二实例中以产生第二多维向量。 可以确定第一多维向量和第二多维向量之间的第一距离度量。

    Systems and methods for image object recognition based on location information and object categories
    6.
    发明授权
    Systems and methods for image object recognition based on location information and object categories 有权
    基于位置信息和对象类别的图像对象识别系统和方法

    公开(公告)号：US09495619B2

    公开(公告)日：2016-11-15

    申请号：US14586033

    申请日：2014-12-30

    Applicant: Facebook, Inc.

    Inventor： Kevin Dechau Tang ,  Lubomir Bourdev ,  Balamanohar Paluri ,  Robert D. Fergus

    IPC: G06K9/00 ,  G06K9/66 ,  G06N3/08 ,  G06K9/62 ,  G06K9/46 ,  G06K9/52

    CPC classification number: G06K9/6256 ,  G06K9/00476 ,  G06K9/00671 ,  G06K9/42 ,  G06K9/4642 ,  G06K9/52 ,  G06K9/6267 ,  G06K9/627 ,  G06K9/66 ,  G06K2009/4666 ,  G06N3/08 ,  G06N3/084

    Abstract: Systems, methods, and non-transitory computer-readable media can identify a set of regions corresponding to a geographical area. A collection of training images can be acquired. Each training image in the collection can be associated with one or more respective recognized objects and with a respective region in the set of regions. Histogram metrics for a plurality of object categories within each region in the set of regions can be determined based at least in part on the collection of training images. A neural network can be developed based at least in part on the histogram metrics for the plurality of object categories within each region in the set of regions and on the collection of training images.

    Abstract translation: 系统，方法和非暂时的计算机可读介质可以识别对应于地理区域的一组区域。 可以获取训练图像的集合。 集合中的每个训练图像可以与一个或多个相应的识别对象以及区域集合中的相应区域相关联。 可以至少部分地基于训练图像的收集来确定该组区域中的每个区域内的多个对象类别的直方图度量。 可以至少部分地基于区域集合中的每个区域内的多个对象类别的直方图度量和训练图像的集合来开发神经网络。

    SYSTEMS AND METHODS FOR DETERMINING VIDEO FEATURE DESCRIPTORS BASED ON CONVOLUTIONAL NEURAL NETWORKS
    7.
    发明申请
    SYSTEMS AND METHODS FOR DETERMINING VIDEO FEATURE DESCRIPTORS BASED ON CONVOLUTIONAL NEURAL NETWORKS 有权
    基于连续神经网络确定视频特征描述符的系统和方法

    公开(公告)号：US20160189009A1

    公开(公告)日：2016-06-30

    申请号：US14585826

    申请日：2014-12-30

    Applicant: Facebook, Inc.

    Inventor： Du Le Hong Tran ,  Balamanohar Paluri ,  Lubomir Bourdev ,  Robert D. Fergus ,  Sumit Chopra

    IPC: G06K9/66 ,  G06K9/52 ,  G06K9/00

    CPC classification number: G06K9/00744 ,  G06N3/0454 ,  G06N3/084

    Abstract: Systems, methods, and non-transitory computer-readable media can acquire video content for which video feature descriptors are to be determined. The video content can be processed based at least in part on a convolutional neural network including a set of two-dimensional convolutional layers and a set of three-dimensional convolutional layers. One or more outputs can be generated from the convolutional neural network. A plurality of video feature descriptors for the video content can be determined based at least in part on the one or more outputs from the convolutional neural network.

    Abstract translation: 系统，方法和非暂时的计算机可读介质可以获取要确定视频特征描述符的视频内容。 可以至少部分地基于包括一组二维卷积层和一组三维卷积层的卷积神经网络来处理视频内容。 可以从卷积神经网络生成一个或多个输出。 可以至少部分地基于来自卷积神经网络的一个或多个输出来确定用于视频内容的多个视频特征描述符。

    SYSTEMS AND METHODS FOR PROVIDING CONTENT
    8.
    发明申请
    SYSTEMS AND METHODS FOR PROVIDING CONTENT 有权

    公开(公告)号：US20210004662A1

    公开(公告)日：2021-01-07

    申请号：US17030157

    申请日：2020-09-23

    Applicant: Facebook, Inc.

    Inventor： Kai Li ,  Fei Yang ,  Balamanohar Paluri

    IPC: G06N3/04 ,  G06F16/783

    Abstract: Systems, methods, and non-transitory computer-readable media can receive a first content item having a set of frames. A binary hash code that represents the first content item is generated using at least an aggregation model and an iterative quantization hash model, the binary hash code being determined based at least in part on the set of frames of the first content item. The binary hash code is stored, wherein a similarity between the first content item and a second content item is capable of being measured based at least in part on a comparison of the binary hash code of the first content item and a binary hash code of the second content item.

Patent Agency Ranking