中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

107 records (took 0.021 seconds)

    Online training and update of factorization machines using alternating least squares optimization
    31.
    发明授权
    Online training and update of factorization machines using alternating least squares optimization 有权

    公开(公告)号：US11049041B2

    公开(公告)日：2021-06-29

    申请号：US15963737

    申请日：2018-04-26

    Applicant: Adobe Inc.

    Inventor： Saayan Mitra ,  Xueyu Mao ,  Viswanathan Swaminathan ,  Somdeb Sarkhel ,  Sheng Li

    IPC: G06N20/00 ,  G06F17/16 ,  G06N5/04

    Abstract: Techniques are disclosed for training of factorization machines (FMs) using a streaming mode alternating least squares (ALS) optimization. A methodology implementing the techniques according to an embodiment includes receiving a datapoint that includes a feature vector and an associated target value. The feature vector includes user identification, subject matter identification, and a context. The target value identifies an opinion of the user relative to the subject matter. The method further includes applying an FM to the feature vector to generate an estimate of the target value, and updating parameters of the FM for training of the FM. The parameter update is based on application of a streaming mode ALS optimization to: the datapoint; the estimate of the target value; and to an updated summation of intermediate calculated terms generated by application of the streaming mode ALS optimization to previously received datapoints associated with prior parameter updates of the FM.

    Latency optimization for digital asset compression
    32.
    发明授权
    Latency optimization for digital asset compression 有权

    公开(公告)号：US10942914B2

    公开(公告)日：2021-03-09

    申请号：US15788146

    申请日：2017-10-19

    Applicant: ADOBE INC.

    Inventor： Viswanathan Swaminathan ,  Saayan Mitra

    IPC: G06F16/00 ,  G06F16/23 ,  G06F16/583 ,  G06F16/174

    Abstract: Embodiments of the present disclosure provide systems, methods, and computer storage media for mitigating delays typically experienced when training codebooks during the encoding process. Instead of training a codebook based on a single digital asset, multiple digital assets determined to have asset characteristics in common can be grouped together to form a group of digital assets, from which a single codebook can be trained. The group of digital assets together form a codebook training set, such that each digital asset therein can be analyzed, in parallel, to expeditiously train a single codebook. A codebook trained in this manner can be employed to encode other digital assets sharing the asset characteristics as those in the codebook training set.

    Trajectory-Based Viewport Prediction for 360-Degree Videos
    33.
    发明申请
    Trajectory-Based Viewport Prediction for 360-Degree Videos 审中-公开

    公开(公告)号：US20200374506A1

    公开(公告)日：2020-11-26

    申请号：US16421276

    申请日：2019-05-23

    Applicant: Adobe Inc.

    Inventor： Stefano Petrangeli ,  Viswanathan Swaminathan ,  Gwendal Brieuc Christian Simon

    IPC: H04N13/194 ,  H04N13/376

    Abstract: In implementations of trajectory-based viewport prediction for 360-degree videos, a video system obtains trajectories of angles of users who have previously viewed a 360-degree video. The angles are used to determine viewports of the 360-degree video, and may include trajectories for a yaw angle, a pitch angle, and a roll angle of a user recorded as the user views the 360-degree video. The video system clusters the trajectories of angles into trajectory clusters, and for each trajectory cluster determines a trend trajectory. When a new user views the 360-degree video, the video system compares trajectories of angles of the new user to the trend trajectories, and selects trend trajectories for a yaw angle, a pitch angle, and a roll angle for the user. Using the selected trend trajectories, the video system predicts viewports of the 360-degree video for the user for future times.

    Prioritizing tile-based virtual reality video streaming using adaptive rate allocation
    34.
    发明授权
    Prioritizing tile-based virtual reality video streaming using adaptive rate allocation 有权

    公开(公告)号：US10595069B2

    公开(公告)日：2020-03-17

    申请号：US15593050

    申请日：2017-05-11

    Applicant: Adobe Inc.

    Inventor： Viswanathan Swaminathan ,  Mohammad Hosseini

    IPC: H04L29/06 ,  H04L12/927 ,  H04N21/2662 ,  H04N21/81 ,  H04N21/462 ,  H04N21/845

    Abstract: The present disclosure includes methods and systems for streaming high-performance virtual reality video using adaptive rate allocation. In particular, an adaptive rate allocation system partitions a panorama video into segments or tiles and assigns priorities to each tile or segment based on input (e.g., a viewport of field-of-view) from a user client device. Further, the adaptive rate allocation system streams each tile or segment to the user client device according to the adaptive rate allocation, which maximizes bandwidth efficiency and video quality. In this manner, the adaptive rate allocation system delivers higher quality content to regions in the panorama video where a user is currently looking/most likely to look.

    Codebook generation for cloud-based video applications
    35.
    发明授权
    Codebook generation for cloud-based video applications 有权

    公开(公告)号：US10264262B2

    公开(公告)日：2019-04-16

    申请号：US15055913

    申请日：2016-02-29

    Applicant: Adobe Inc.

    Inventor： Viswanathan Swaminathan ,  Rashmi Mittal

    IPC: H04N19/13 ,  H04N19/176 ,  H04N19/196

    Abstract: Techniques are disclosed for the improvement of vector quantization (VQ) codebook generation. The improved codebooks may be used for compression in cloud-based video applications. VQ achieves compression by vectorizing input video streams, matching those vectors to codebook vector entries, and replacing them with indexes of the matched codebook vectors along with residual vectors to represent the difference between the input stream vector and the codebook vector. The combination of index and residual is generally smaller than the input stream vector which they collectively encode, thus providing compression. The improved codebook may be generated from training video streams by grouping together similar types of data (e.g., image data, motion data, control data) from the video stream to generate longer vectors having higher dimensions and greater structure. This improves the ability of VQ to remove redundancy and thus increase compression efficiency. Storage space is thus reduced and video transmission may be faster.

    View synthesis with spatial and rotational consistency
    37.
    发明授权
    View synthesis with spatial and rotational consistency 有权

    公开(公告)号：US12051175B2

    公开(公告)日：2024-07-30

    申请号：US17097600

    申请日：2020-11-13

    Applicant: ADOBE INC.

    Inventor： Stefano Petrangeli ,  Viswanathan Swaminathan ,  Haoliang Wang ,  YoungJoong Kwon

    IPC: G06N3/08 ,  G06N3/045 ,  G06T3/604 ,  G06T3/606

    CPC classification number: G06T3/604 ,  G06N3/045 ,  G06N3/08 ,  G06T3/606 ,  G06T2207/20081 ,  G06T2207/20084

    Abstract: Methods, system, and computer storage media are provided for novel view synthesis. An input image depicting an object is received and utilized to generate, via a neural network, a target view image. In exemplary aspects, additional view images are also generated within the same pass of the neural network. A loss is determined based on the target view image and additional view images and is used to modify the neural network to reduce errors. In some aspects, a rotated view image is generated by warping a ground truth image from an initial angle to a rotated view angle that matches a view angle of an image synthesized via the neural network, such as a target view image. The rotated view image and the synthesized image matching the rotated view angle (e.g., a target view image) are utilized to compute a rotational loss.

Patent Agency Ranking