中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

237 records (took 0.034 seconds)

    HASH CODES FOR IMAGES
    72.
    发明申请
    HASH CODES FOR IMAGES 有权
    图像的HASH代码

    公开(公告)号：US20160358043A1

    公开(公告)日：2016-12-08

    申请号：US14732463

    申请日：2015-06-05

    Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

    Inventor： Yadong Mu ,  Zhu Liu

    IPC: G06K9/66 ,  G06F17/30 ,  G06N3/04 ,  G06K9/62

    CPC classification number: G06K9/66 ,  G06F17/30256 ,  G06F17/3028 ,  G06F17/30598 ,  G06K9/6217 ,  G06N3/04 ,  G06N3/0454

    Abstract: A method includes receiving, at a neural network, a subset of images of a plurality of images of a training image set. The method includes training the neural network by iteratively adjusting parameters of the neural network based on concurrent application of multiple loss functions to the subset of images. The multiple loss functions include a classification loss function and a hashing loss function. The classification loss function is associated with an image classification function that extracts image features from an image. The hashing loss function is associated with a hashing function that generates a hash code for the image.

    Abstract translation: 一种方法包括在神经网络处接收训练图像集合的多个图像的图像的子集。 该方法包括通过对基于图像子集的多个损失函数的并发应用，迭代地调整神经网络的参数来训练神经网络。 多重损失函数包括分类丢失函数和散列丢失函数。 分类丢失函数与从图像中提取图像特征的图像分类功能相关联。 哈希丢失函数与为图像生成哈希码的散列函数相关联。

    Method and apparatus for providing secure image encryption and decryption
    74.
    发明授权
    Method and apparatus for providing secure image encryption and decryption 有权
    用于提供安全图像加密和解密的方法和装置

    公开(公告)号：US09396310B2

    公开(公告)日：2016-07-19

    申请号：US13942260

    申请日：2013-07-15

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Gustavo de los Reyes ,  Andrea Forte ,  Juan A. Garay ,  David Crawford Gibbon ,  Zhu Liu ,  Evgene Vahlis ,  Eric Zavesky

    IPC: G06F21/62 ,  G06F21/00 ,  H04N1/32 ,  H04N1/44 ,  G09C5/00 ,  H04L9/08

    CPC classification number: G06F21/6245 ,  G06F21/6227 ,  G06F2221/2107 ,  G09C5/00 ,  H04L9/088 ,  H04N1/32272 ,  H04N1/4486

    Abstract: Methods, non-transitory computer readable media and apparatuses for decrypting an image are disclosed. For example, a method captures a portion of an encrypted image and decrypts the portion of the image using a decryption key. The portion of the image contains partial information for an adjacent portion of the image. The method then displays the portion of the image that is decrypted and also displays the adjacent portion of the image using the partial information for the adjacent portion of the image. Another method includes capturing a first portion of an image that is encrypted using a first key and a second key, decrypting the first portion of the image using a first key and displaying the first portion of the image that is decrypted.

    Abstract translation: 公开了用于解密图像的方法，非暂时计算机可读介质和装置。 例如，一种方法捕获加密图像的一部分，并使用解密密钥对图像的部分进行解密。 图像的部分包含图像的相邻部分的部分信息。 该方法然后显示被解密的图像的部分，并且还使用图像的相邻部分的部分信息来显示图像的相邻部分。 另一种方法包括捕获使用第一密钥和第二密钥加密的图像的第一部分，使用第一密钥解密图像的第一部分并显示解密的图像的第一部分。

    Method and apparatus for automated analysis and identification of a person in image and video content
    76.
    发明授权
    Method and apparatus for automated analysis and identification of a person in image and video content 有权
    用于自动分析和识别图像和视频内容中的人的方法和装置

    公开(公告)号：US09129151B2

    公开(公告)日：2015-09-08

    申请号：US14308050

    申请日：2014-06-18

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Zhu Liu ,  Andrea Basso ,  Lee Begeja ,  David C. Gibbon ,  Bernard S. Renger ,  Behzad Shahraray ,  Eric Zavesky

    IPC: G06K9/00 ,  G06K9/68 ,  G06F17/30

    CPC classification number: G06K9/00288 ,  G06F17/30247 ,  G06F17/30259 ,  G06F17/30268 ,  G06F17/30793 ,  G06K9/00536 ,  G06K9/00677 ,  G06K2009/00328

    Abstract: A method, apparatus, and computer readable medium for identifying a person in an image includes an image analyzer. The image analyzer determines the content of an image such as a person, location, and object shown in the image. A person in the image may be identified based on the content and event data stored in a database. Event data includes information concerning events and related people, locations, and objects determined from other images and information. Identification metadata is generated and linked to each analyzed image and comprises information determined during image analysis. Tags for images are generated based on identification metadata. The event database can be queried to identify particular people, locations, objects, and events depending on a user's request.

    Abstract translation: 用于识别图像中的人的方法，装置和计算机可读介质包括图像分析器。 图像分析仪确定图像中显示的人物，位置和对象等图像的内容。 可以基于存储在数据库中的内容和事件数据来识别图像中的人。 事件数据包括有关事件和相关人员，位置以及从其他图像和信息确定的对象的信息。 生成识别元数据并链接到每个分析的图像，并且包括在图像分析期间确定的信息。 基于身份元数据生成图像标签。 可以查询事件数据库，以根据用户的请求识别特定的人员，位置，对象和事件。

    System and method for notification of event of interest during a video conference
    78.
    发明授权
    System and method for notification of event of interest during a video conference 有权
    在视频会议期间通知感兴趣的事件的系统和方法

    公开(公告)号：US09071728B2

    公开(公告)日：2015-06-30

    申请号：US14202615

    申请日：2014-03-10

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Lee Begeja ,  Zhu Liu ,  Bernard S Renger ,  Behzad Shahraray ,  Eric Zavesky ,  Andrea Basso ,  David Crawford Gibbon ,  Sumit Kumar

    IPC: H04N7/15 ,  H04N7/14

    CPC classification number: H04N7/15 ,  H04N7/147 ,  H04N7/155

    Abstract: A computer implemented method is disclosed, the method including but not limited to detecting an event of interest in video conference data for a plurality of video conference participants and notifying an end user of the event of interest. A computer readable medium is also disclosed for containing a computer program for performing the method. A computer implemented method is also disclosed for receiving at an end user device, a notification of an event of interest in a video teleconference, the method including but not limited to receiving at an end user device from a notification indicating a detection of the event of interest in video conference data from the video teleconference for a plurality of video conference participants; and sending data from the end user device to the server requesting a transcription of comments from the speaker in video teleconference.

    Abstract translation: 公开了一种计算机实现的方法，所述方法包括但不限于检测多个视频会议参与者的视频会议数据中的兴趣事件，并通知终端用户感兴趣的事件。 还公开了一种用于包含用于执行该方法的计算机程序的计算机可读介质。 还公开了一种计算机实现的方法，用于在终端用户设备处接收视频电话会议中感兴趣的事件的通知，所述方法包括但不限于在终端用户设备处接收指示检测到的事件的通知 对于多个视频会议参与者的视频电话会议对视频会议数据的兴趣; 并从终端用户设备发送数据到服务器，请求在视频电话会议中从扬声器转发评论。

    System And Method For Generating Media Bookmarks
    79.
    发明申请
    System And Method For Generating Media Bookmarks 有权
    用于生成媒体书签的系统和方法

    公开(公告)号：US20140164403A1

    公开(公告)日：2014-06-12

    申请号：US14181963

    申请日：2014-02-17

    Applicant: AT&T Intellectual Property I, L.P.

    Inventor： Behzad Shahraray ,  Andrea Basso ,  Lee Begeja ,  David C. Gibbon ,  Zhu Liu ,  Bernard S. Renger

    IPC: G06F17/30

    CPC classification number: G06F17/30784 ,  G06F17/3082 ,  G06F17/30849 ,  G06F17/30858 ,  G06F17/30876 ,  G06F17/30884 ,  G11B27/005 ,  G11B27/34

    Abstract: Disclosed herein are systems, methods, and computer-readable media for transmedia video bookmarks, the method comprising receiving a first place marker and a second place marker for a segment of video media, extracting metadata from the video media between the first and second place markers, normalizing the extracted metadata, storing the normalized metadata, first place marker, and second place marker as a video bookmark, and retrieving the media represented by the video bookmark upon request from a user. Systems can aggregate video bookmarks from multiple sources and refine the first place marker and second place marker based on the aggregated video bookmarks. Metadata can be extracted by analyzing text or audio annotations. Metadata can be normalized by generating a video thumbnail representing the video media between the first place marker and the second place marker. Multiple video bookmarks may be searchable by metadata or by the video thumbnail visually.

    Abstract translation: 本文公开了用于跨媒体视频书签的系统，方法和计算机可读介质，所述方法包括：接收第一位置标记和用于视频介质段的第二位置标记，从第一和第二位置标记之间的视频介质提取元数据 归一化所提取的元数据，存储归一化元数据，第一地点标记和第二地方标记作为视频书签，以及根据用户的请求检索由该视频书签表示的媒体。 系统可以聚合来自多个来源的视频书签，并基于聚合的视频书签来优化第一个地方标记和第二个地方标记。 可以通过分析文本或音频注释来提取元数据。 可以通过生成表示第一位置标记和第二位置标记之间的视频介质的视频缩略图来对元数据进行归一化。 可以通过元数据或视频缩略图可视地搜索多个视频书签。

    Method and System for Time-Multiplexed Shared Display
    80.
    发明申请
    Method and System for Time-Multiplexed Shared Display 有权
    时间多路复用共享显示方法与系统

    公开(公告)号：US20130235172A1

    公开(公告)日：2013-09-12

    申请号：US13868685

    申请日：2013-04-23

    Applicant: AT&T INTELLECTUAL PROPERTY I, L.P.

    Inventor： Behzad Shahraray ,  David C. Gibbon ,  Zhu Liu ,  Bernard S. Renger

    IPC: H04N3/02

    CPC classification number: H04N3/02 ,  G02B27/2264 ,  G09G3/003 ,  G09G5/397 ,  G09G2358/00

    Abstract: A method is provided for sharing a display. The method includes displaying periodically a first image sequence on the display in synchronicity with a first signal, and displaying periodically a second image sequence on the display in synchronicity with a second signal. The method also includes selecting by a user the first image sequence for viewing, and shuttering periodically a set of goggles for the user in synchronicity with the first signal. A method is provided for sharing a display. The method includes displaying periodically a private image sequence on the display in synchronicity with a first signal, and displaying periodically a non-private image sequence on the display. In the method, the private image sequence and the non-private image sequence combine to form a public image sequence on the display. A system is provided for sharing a display.

    Abstract translation: 提供了一种用于共享显示器的方法。 该方法包括与第一信号同步地在显示器上周期性地显示第一图像序列，并且与第二信号同步地在显示器上周期性地显示第二图像序列。 该方法还包括用户选择用于观看的第一图像序列，并且与第一信号同步地周期性地对用户的一组护目镜进行快门。 提供了一种用于共享显示器的方法。 该方法包括与第一信号同步地在显示器上周期性地显示专用图像序列，并且在显示器上周期性地显示非私有图像序列。 在该方法中，私有图像序列和非私人图像序列组合以在显示器上形成公共图像序列。 提供用于共享显示器的系统。

Patent Agency Ranking