中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

60 records (took 0.013 seconds)

    AUTOMATED DECISIONS BASED ON DESCRIPTIVE MODELS
    1.
    发明申请
    AUTOMATED DECISIONS BASED ON DESCRIPTIVE MODELS 审中-公开

    公开(公告)号：WO2019199905A1

    公开(公告)日：2019-10-17

    申请号：PCT/US2019/026685

    申请日：2019-04-09

    Applicant: FACEBOOK, INC

    Inventor： HARRISON, Jason, Francis ,  HWANG, Eric, W. ,  NALLAMOTHU, Rahul ,  RAZZAQ, Shahid

    IPC: H04N21/4788 ,  H04N21/44 ,  H04N21/4545 ,  H04N21/4728 ,  H04N21/234 ,  H04N21/4223

    Abstract: In one embodiment, a method includes accessing input data from one or more different input sources. The input sources include: one or more cameras, one or more microphones, and a social graph maintained by a social-networking system. Based on the input data, generating a current descriptive model for a current audio-video communication session that comprises one or more descriptive characteristics about (1) an environment associated with the current audio- video communication session, (2) one or more people within the environment, or (3) one or more contextual elements associated with the current audio-video communication session. The method also includes generating one or more instructions for the current audio-video communication session that are based the one or more descriptive characteristics; and sending the one or more instructions to a computing device associated with the one or more cameras and the one or more microphones.

    METHOD AND APPARATUS FOR FILTERING VIDEO
    3.
    发明申请
    METHOD AND APPARATUS FOR FILTERING VIDEO 审中-公开

    公开(公告)号：WO2018117428A1

    公开(公告)日：2018-06-28

    申请号：PCT/KR2017/012974

    申请日：2017-11-16

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： YUN, Ji-hwan ,  KIM, Min-seo ,  JUNG, Jae-yun

    IPC: H04N21/454 ,  H04N21/4545 ,  H04N5/445

    Abstract: An artificial intelligence (AI) system for simulating functions such as recognition, determination, and so forth of a human brain by using a mechanical learning algorithm such as deep learning, or the like, and an application thereof are provided. A method of filtering video by a device is provided. The method includes selecting at least one previous frame preceding a current frame being played from among a plurality of frames included in the video, generating metadata regarding the selected at least one previous frame, predicting harmfulness of at least one next frame to be displayed on the device after playback of the current frame, based on the generated metadata, and filtering the next frame based on the predicted harmfulness.

    UPLOAD OF MULTIMEDIA CONTENT
    5.
    发明申请
    UPLOAD OF MULTIMEDIA CONTENT 审中-公开
    上载多媒体内容

    公开(公告)号：WO2017048168A1

    公开(公告)日：2017-03-23

    申请号：PCT/SE2015/050977

    申请日：2015-09-18

    Applicant: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)

    Inventor： STRÖM, Jacob ,  ARNGREN, Tommy

    IPC: H04N21/23 ,  H04N21/2743 ,  H04N21/4545 ,  H04H60/35 ,  G06Q50/00

    CPC classification number: H04N21/23 ,  G06Q50/01 ,  H04H60/48 ,  H04N21/2743 ,  H04N21/45457

    Abstract: A full multimedia content is sent to end users from a network node (2; 2A). The end users select a respective personalized multimedia content from the full multimedia content and send a respective index associated with the respective selected personalized multimedia content to a network node (2; 2B) to trigger uploading of the respective selected personalized multimedia content or a version thereof on a social networking server (4) on behalf of the end users. The embodiments thereby enable end users to upload personalized multimedia content on their accounts at social networking servers (4) also in situations with limited uplink capacity by merely sending indices associated with the personalized multimedia content instead of the actual multimedia content itself.

    Abstract translation: 从网络节点（2; 2A）向最终用户发送完整的多媒体内容。 最终用户从完整的多媒体内容中选择相应的个性化多媒体内容，并将与各个所选择的个性化多媒体内容相关联的相应索引发送到网络节点（2; 2B），以触发相应选择的个性化多媒体内容的上传或其版本 在社交网络服务器（4）上代表终端用户。 这些实施例使终端用户能够通过仅发送与个性化多媒体内容相关联的索引而不是实际的多媒体内容本身，在社交网络服务器（4）的上述个人化多媒体内容上也可以在具有有限的上行链路容量的情况下上传个性化

    DETERMINING A REGION OF INTEREST ON THE BASIS OF A HEVC-TILED VIDEO STREAM
    6.
    发明申请
    DETERMINING A REGION OF INTEREST ON THE BASIS OF A HEVC-TILED VIDEO STREAM 审中-公开
    确定一个基于热镀锌视频流的基础上的一个地区

    公开(公告)号：WO2015197815A1

    公开(公告)日：2015-12-30

    申请号：PCT/EP2015/064511

    申请日：2015-06-26

    Applicant: KONINKLIJKE KPN N.V. ,  NEDERLANDSE ORGANISATIE VOOR TOEGEPAST-NATUURWETENSCHAPPELIJK ONDERZOEK TNO

    Inventor： THOMAS, Emmanuel ,  VAN BRANDENBURG, Ray ,  VAN DEVENTER, Mattijs Oskar

    IPC: H04N21/218 ,  H04N21/2343 ,  H04N21/4728 ,  H04N21/6587 ,  H04N21/4545 ,  H04N21/845 ,  H04N21/858 ,  H04N13/00 ,  H04N13/04

    CPC classification number: H04N21/8586 ,  H04N19/119 ,  H04N19/167 ,  H04N19/174 ,  H04N19/85 ,  H04N21/2343 ,  H04N21/234327 ,  H04N21/234363 ,  H04N21/440263 ,  H04N21/4728 ,  H04N21/6587 ,  H04N21/8455 ,  H04N21/85406

    Abstract: A method is described for determining a region-of-interest (ROI) for a client device on the basis of at least one HEVC-tiled (panorama) video stream wherein the method comprises: receiving a ROI video stream for rendering a first ROI defining a first sub-region within the full image region of said HEVC-tiled video stream, the positions of HEVC tiles in said HEVC-tiled panorama video being defined by tile position information; providing ROI position information associated with at least one video frame of said ROI video stream, said ROI position information comprising at least first position of said first ROI; identifying one or more HEVC tiles of said HEVC-tiled video stream on the basis of said ROI position information and said tile position information, preferably one or more HEVC tiles that overlap with said first ROI; and, requesting video data associated with said one or more identified HEVC tiles for rendering a second ROI defining a second sub-region within the full image region of said HEVC-tiled video stream.

    Abstract translation: 描述了一种用于基于至少一个HEVC平铺（全景）视频流来确定客户端设备的感兴趣区域（ROI）的方法，其中该方法包括：接收用于呈现第一ROI定义的ROI视频流 在所述HEVC平铺视频流的整个图像区域内的第一子区域，所述HEVC平铺全景视频中的HEVC瓦片的位置由瓦片位置信息定义; 提供与所述ROI视频流的至少一个视频帧相关联的ROI位置信息，所述ROI位置信息至少包括所述第一ROI的第一位置; 基于所述ROI位置信息和所述瓦片位置信息，优选地与所述第一ROI重叠的一个或多个HEVC瓦片来识别所述HEVC平铺视频流的一个或多个HEVC瓦片; 以及请求与所述一个或多个所识别的HEVC瓦片相关联的视频数据，用于渲染在所述HEVC平铺视频流的完整图像区域内定义第二子区域的第二ROI。

    SYSTEMS AND METHODS TO PROVIDE ADAPTIVE PLAY SETTINGS
    9.
    发明申请
    SYSTEMS AND METHODS TO PROVIDE ADAPTIVE PLAY SETTINGS 审中-公开

    公开(公告)号：WO2022203737A1

    公开(公告)日：2022-09-29

    申请号：PCT/US2021/064452

    申请日：2021-12-20

    Applicant: ROVI GUIDES, INC.

    Inventor： CHANDRASHEKAR, Padmassri ,  EMMANUEL, Daina

    IPC: H04N21/262 ,  H04N21/45 ,  H04N21/4545 ,  H04N21/458 ,  H04N21/475 ,  H04N21/845

    Abstract: Systems and methods are provided for applying adaptive play settings to a media asset. One example method includes identifying a media asset selected for playback and retrieving a plurality of user preferences. The user preferences correlate a play function to a type of a segment of a media asset. A plurality of segments in the media asset selected for playback are identified and each of the plurality of segments has a respective type. In response to identifying a plurality of segments in the media asset selected for playback, a respective play function is assigned to each of the respective plurality of segments based on the respective type of each of the plurality of segments.

    视频封面生成方法、装置及电子设备
    10.
    发明申请
    视频封面生成方法、装置及电子设备 审中-公开

    公开(公告)号：WO2021004247A1

    公开(公告)日：2021-01-14

    申请号：PCT/CN2020/096719

    申请日：2020-06-18

    Applicant: 北京字节跳动网络技术有限公司

    Inventor： 黄凯 ,  王长虎

    IPC: H04N21/44 ,  G06K9/00 ,  H04N21/4545 ,  H04N21/466 ,  H04N21/475

    Abstract: 本公开实施例中提供了一种视频封面生成方法、装置及电子设备，属于图像处理技术领域，该方法包括：对目标视频进行解析，得到多个解析图像；对所述多个解析图像进行聚类处理，得到多个候选封面图像；基于对所述候选封面图像中包含的目标对象执行的关键点检测结果，对所述多个候选封面图像中包含的目标对象执行视线检测和睁眼检测，以过滤掉不符合预设要求的候选封面图像；基于图像质量评价网络对过滤后剩余的候选封面图像的质量评分，从过滤后剩余的候选封面图像中选取目标图像作为所述目标视频的最终封面图像。通过本公开的处理方案，能够自动生成高质量的视频封面。

Patent Agency Ranking