中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

12 records (took 0.017 seconds)

    Methods and systems for differentiating synthetic and non-synthetic images
    1.
    发明授权
    Methods and systems for differentiating synthetic and non-synthetic images 有权
    用于区分合成和非合成图像的方法和系统

    公开(公告)号：US09558422B2

    公开(公告)日：2017-01-31

    申请号：US15004656

    申请日：2016-01-22

    Applicant: Facebook, Inc.

    Inventor： Apostolos Lerios ,  Dirk John Stoop ,  Ryan Mack ,  Lubomir Dimitrov Bourdev ,  Balmanohar Paluri

    IPC: G06K9/00 ,  G06K9/46 ,  G06T9/00 ,  H04N19/60 ,  G06K9/62 ,  H04N19/172 ,  H04N19/12 ,  H04N19/136 ,  H04N19/27 ,  H04N19/85 ,  H04N19/40

    CPC classification number: G06K9/4652 ,  G06K9/4604 ,  G06K9/4642 ,  G06K9/6202 ,  G06K9/6267 ,  G06T9/00 ,  H04N19/12 ,  H04N19/136 ,  H04N19/172 ,  H04N19/27 ,  H04N19/40 ,  H04N19/60 ,  H04N19/85 ,  H04N19/86

    Abstract: The techniques introduced here include a system and method for transcoding multimedia content based on the results of content analysis. The determination of specific transcoding parameters, used for transcoding multimedia content, can be performed by utilizing the results of content analysis of the multimedia content. One of the results of the content analysis is the determination of image type of any images included in the multimedia content. The content analysis uses one or more of several techniques, including analyzing content metadata, examining colors of contiguous pixels in the content, using histogram analysis, using compression distortion analysis, analyzing image edges, or examining user provided inputs. Transcoding the multimedia content can include adapting the content to the constraints in delivery and display, processing and storage of user computing devices.

    Abstract translation: 这里介绍的技术包括基于内容分析结果对多媒体内容进行代码转换的系统和方法。 可以通过利用多媒体内容的内容分析结果来执行用于代码转换多媒体内容的特定代码转换参数的确定。 内容分析的结果之一是确定包含在多媒体内容中的任何图像的图像类型。 内容分析使用几种技术中的一种或多种，​​包括分析内容元数据，使用直方图分析，使用压缩失真分析，分析图像边缘或检查用户提供的输入来检查内容中连续像素的颜色。 多媒体内容的转码可以包括使内容适应于用户计算设备的传送和显示，处理和存储中的约束。

    POSE-ALIGNED NETWORKS FOR DEEP ATTRIBUTE MODELING
    2.
    发明申请
    POSE-ALIGNED NETWORKS FOR DEEP ATTRIBUTE MODELING 有权
    用于深度属性建模的POSE对齐网络

    公开(公告)号：US20150139485A1

    公开(公告)日：2015-05-21

    申请号：US14175314

    申请日：2014-02-07

    Applicant: Facebook, Inc.

    Inventor： Lubomir Dimitrov Bourdev

    IPC: G06K9/00 ,  G06K9/66

    CPC classification number: G06K9/00362 ,  G06K9/4628 ,  G06K9/6292

    Abstract: Technology is disclosed for inferring human attributes from images of people. The attributes can include, for example, gender, age, hair, and/or clothing. The technology uses part-based models, e.g., Poselets, to locate multiple normalized part patches from an image. The normalized part patches are provided into trained convolutional neural networks to generate feature data. Each convolution neural network applies multiple stages of convolution operations to one part patch to generate a set of fully connected feature data. The feature data for all part patches are concatenated and then provided into multiple trained classifiers (e.g., linear support vector machines) to predict attributes of the image.

    Abstract translation: 公开了用于从人的图像推断人类属性的技术。 这些属性可以包括例如性别，年龄，头发和/或服装。 该技术使用基于部分的模型（例如，Poselets）从图像中定位多个归一化部分补丁。 将归一化部分补丁提供到训练卷积神经网络中以产生特征数据。 每个卷积神经网络将卷积操作的多个阶段应用于一个零件补丁以产生一组完全连接的特征数据。 所有部分补丁的特征数据被级联，然后提供给多个训练有素的分类器（例如，线性支持向量机），以预测图像的属性。

    Pose-Aligned Networks for Deep Attribute Modeling
    3.
    发明申请
    Pose-Aligned Networks for Deep Attribute Modeling 审中-公开

    公开(公告)号：US20190303660A1

    公开(公告)日：2019-10-03

    申请号：US16443707

    申请日：2019-06-17

    Applicant: Facebook, Inc.

    Inventor： Lubomir Dimitrov Bourdev

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62

    Abstract: In one embodiment, a method includes locating a plurality of part patches from an image, wherein each part patch comprises at least a portion of the image corresponding to a recognized human body portion or pose, and wherein each part patch is associated with a respective detection score larger than a threshold score, wherein the detection score is determined based on a comparison between the part patch with multiple training patches, generating a plurality of sets of feature data by processing each of the plurality of part patches with a plurality of convolutional neural networks, respectively, and determining whether a human attribute exists in the image based on the plurality of sets of feature data.

    Pose-aligned networks for deep attribute modeling
    4.
    发明授权
    Pose-aligned networks for deep attribute modeling 有权

    公开(公告)号：US10402632B2

    公开(公告)日：2019-09-03

    申请号：US15214029

    申请日：2016-07-19

    Applicant: Facebook, Inc.

    Inventor： Lubomir Dimitrov Bourdev

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62

    Abstract: Technology is disclosed for inferring human attributes from images of people. The attributes can include, for example, gender, age, hair, and/or clothing. The technology uses part-based models, e.g., Poselets, to locate multiple normalized part patches from an image. The normalized part patches are provided into trained convolutional neural networks to generate feature data. Each convolution neural network applies multiple stages of convolution operations to one part patch to generate a set of fully connected feature data. The feature data for all part patches are concatenated and then provided into multiple trained classifiers (e.g., linear support vector machines) to predict attributes of the image.

    Pose-aligned networks for deep attribute modeling
    5.
    发明授权
    Pose-aligned networks for deep attribute modeling 有权
    用于深层属性建模的姿态对齐网络

    公开(公告)号：US09400925B2

    公开(公告)日：2016-07-26

    申请号：US14175314

    申请日：2014-02-07

    Applicant: Facebook, Inc.

    Inventor： Lubomir Dimitrov Bourdev

    IPC: G06K9/00 ,  G06K9/46 ,  G06K9/62

    CPC classification number: G06K9/00362 ,  G06K9/4628 ,  G06K9/6292

    Abstract: Technology is disclosed for inferring human attributes from images of people. The attributes can include, for example, gender, age, hair, and/or clothing. The technology uses part-based models, e.g., Poselets, to locate multiple normalized part patches from an image. The normalized part patches are provided into trained convolutional neural networks to generate feature data. Each convolution neural network applies multiple stages of convolution operations to one part patch to generate a set of fully connected feature data. The feature data for all part patches are concatenated and then provided into multiple trained classifiers (e.g., linear support vector machines) to predict attributes of the image.

    Abstract translation: 公开了用于从人的图像推断人类属性的技术。 这些属性可以包括例如性别，年龄，头发和/或服装。 该技术使用基于部分的模型（例如，Poselets）从图像中定位多个归一化部分补丁。 将归一化部分补丁提供到训练卷积神经网络中以产生特征数据。 每个卷积神经网络将卷积操作的多个阶段应用于一个零件补丁以产生一组完全连接的特征数据。 所有部分补丁的特征数据被级联，然后提供给多个训练有素的分类器（例如，线性支持向量机），以预测图像的属性。

    Identifying Content Items Using a Deep-Learning Model
    8.
    发明申请
    Identifying Content Items Using a Deep-Learning Model 审中-公开

    公开(公告)号：US20170132510A1

    公开(公告)日：2017-05-11

    申请号：US14981413

    申请日：2015-12-28

    Applicant: Facebook, Inc.

    Inventor： Balmanohar Paluri ,  Oren Rippel ,  Piotr Dollar ,  Lubomir Dimitrov Bourdev

    IPC: G06N3/08 ,  H04L29/08

    CPC classification number: G06N3/08 ,  G06N3/0454 ,  H04L67/10 ,  H04L67/1097

    Abstract: In one embodiment, a method may include receiving a first content item. A first embedding of the first content item may be determined and may corresponds to a first point in an embedding space. The embedding space may include a plurality of second points corresponding to a plurality of second embeddings of second content items. The embeddings are determined using a deep-learning model. The points are located in one or more clusters in the embedding space, which are each associated with a class of content items. Locations of points within clusters may be based on one or more attributes of the respective corresponding content items. Second content items that are similar to the first content item may be identified based on the locations of the first point and the second points and on particular clusters that the second points corresponding to the identified second content items are located in.

    POSE-ALIGNED NETWORKS FOR DEEP ATTRIBUTE MODELING
    10.
    发明申请
    POSE-ALIGNED NETWORKS FOR DEEP ATTRIBUTE MODELING 审中-公开

    公开(公告)号：US20160328606A1

    公开(公告)日：2016-11-10

    申请号：US15214029

    申请日：2016-07-19

    Applicant: Facebook, Inc.

    Inventor： Lubomir Dimitrov Bourdev

    IPC: G06K9/00 ,  G06K9/62 ,  G06K9/46

    CPC classification number: G06K9/00362 ,  G06K9/4628 ,  G06K9/6292

    Abstract: Technology is disclosed for inferring human attributes from images of people. The attributes can include, for example, gender, age, hair, and/or clothing. The technology uses part-based models, e.g., Poselets, to locate multiple normalized part patches from an image. The normalized part patches are provided into trained convolutional neural networks to generate feature data. Each convolution neural network applies multiple stages of convolution operations to one part patch to generate a set of fully connected feature data. The feature data for all part patches are concatenated and then provided into multiple trained classifiers (e.g., linear support vector machines) to predict attributes of the image.

Patent Agency Ranking