利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

5157 条记录 (耗时 0.04 秒)

    Forecasting multiple poses based on a graphical image
    41.
    发明授权
    Forecasting multiple poses based on a graphical image 有权

    公开(公告)号：US10096125B1

    公开(公告)日：2018-10-09

    申请号：US15481564

    申请日：2017-04-07

    申请人： Adobe Systems Incorporated

    发明人： Jimei Yang ,  Yu-Wei Chao ,  Scott Cohen ,  Brian Price

    IPC分类号： G06K9/62 ,  G06T7/246 ,  G06N3/04 ,  G06N5/04

    摘要： A forecasting neural network receives data and extracts features from the data. A recurrent neural network included in the forecasting neural network provides forecasted features based on the extracted features. In an embodiment, the forecasting neural network receives an image, and features of the image are extracted. The recurrent neural network forecasts features based on the extracted features, and pose is forecasted based on the forecasted features. Additionally or alternatively, additional poses are forecasted based on additional forecasted features.

    Buffering in HTTP streaming client
    44.
    发明授权
    Buffering in HTTP streaming client 有权

    公开(公告)号：US10091269B2

    公开(公告)日：2018-10-02

    申请号：US14740547

    申请日：2015-06-16

    申请人： Adobe Systems Incorporated

    发明人： Viswanathan Swaminathan ,  Saayan Mitra

    IPC分类号： G06F15/16 ,  H04L29/08 ,  H04N21/236 ,  H04N21/2389 ,  H04L29/06

    摘要： A buffer model in an HTTP streaming client may include receiving a first content fragment of a first content stream in response to a first HTTP request. It may also include receiving a second content fragment of a second content stream in response to a second HTTP request. The buffer model may further include storing the first and second content fragments in first and second buffers of a plurality of configurable buffers. The first and second content fragments may be multiplexed into a third buffer of the plurality of buffers. The multiplexed first and second content fragments may be stored in a fourth buffer of the plurality of buffers for playback. The buffer model may be implemented by an application. The buffers may be designed based on one or more constraints.

    Homography-assisted perspective drawing
    45.
    发明授权
    Homography-assisted perspective drawing 有权

    公开(公告)号：US10089759B2

    公开(公告)日：2018-10-02

    申请号：US15012649

    申请日：2016-02-01

    申请人： Adobe Systems Incorporated

    发明人： Geoffrey Dowd ,  Geoffrey Oxholm

    IPC分类号： G06T11/20 ,  G06T11/60 ,  G06F3/0484 ,  G06T7/80

    摘要： Systems and methods disclosed herein provide drawing assistance to a user that improves the user's ability to draw accurate perspective drawings. In general, a drawing assistance system provides a homography that annotates guidelines over an image and connects lined features of the image to a corresponding vanishing point. More specifically, the homography provides a perspective grid to the user that assists the user in adding drawing strokes to a drawing using the proper perspective. In addition, the drawing assistance system can adjust a user's drawing stroke to properly align with a vanishing point. Further, in some embodiments, the drawing assistance system allows a user to add an asset into a drawing such that the asset is displayed in the proper perspective, even after a user moves the asset within a drawing.

    Metric Forecasting Employing a Similarity Determination in a Digital Medium Environment
    46.
    发明申请
    Metric Forecasting Employing a Similarity Determination in a Digital Medium Environment 审中-公开

    公开(公告)号：US20180276691A1

    公开(公告)日：2018-09-27

    申请号：US15465449

    申请日：2017-03-21

    申请人： Adobe Systems Incorporated

    发明人： Chunyuan Li ,  Hung Hai Bui ,  Mohammad Ghavamzadeh ,  Georgios Theocharous

    IPC分类号： G06Q30/02 ,  G06N3/08

    CPC分类号： G06Q30/0202 ,  G06N3/0445 ,  G06N3/08 ,  G06Q30/0205

    摘要： Metric forecasting techniques and systems in a digital medium environment are described that leverage similarity of elements, one to another, in order to generate a forecast value for a metric for a particular element. In one example, training data is received that describes a time series of values of the metric for a plurality of elements. The model is trained to generate the forecast value of the metric, the training using machine learning of a neural network based on the training data. The training includes generating dimensional-transformation data configured to transform the training data into a simplified representation to determine similarity of the plurality of elements, one to another, with respect to the metric over the time series. The training also includes generating model parameters of the neural network based on the simplified representation to generate the forecast value of the metric.