知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

10 records (took 0.024 seconds)

    METHOD AND SYSTEM FOR HARMONIZING PERCEPTUAL QUALITY OF MULTIPLE APPLICATIONS IN EXTENDED REALITY (XR) ENVIRONMENT
    1.
    发明申请
    METHOD AND SYSTEM FOR HARMONIZING PERCEPTUAL QUALITY OF MULTIPLE APPLICATIONS IN EXTENDED REALITY (XR) ENVIRONMENT 有权

    公开(公告)号：US20240378803A1

    公开(公告)日：2024-11-14

    申请号：US18638057

    申请日：2024-04-17

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Ravi SURANA ,  Prasenjit CHAKRABORTY ,  Erik GUTTMAN ,  Hyunkoo YANG ,  Naveen KOLATI ,  Siva Prasad GUNDUR ,  Abhishek SONI ,  Aranya SAMAIYAR

    IPC: G06T17/00 ,  G06T7/70

    Abstract: A method and system for harmonizing perceptual, quality of multiple applications in extended reality (XR) environment are provided. The method includes receiving, by an XR device, at least one media stream received from each application of plurality of applications in the XR device, determining a perceptual quality score for at least one media stream received from each application of the plurality of applications, determining at least one candidate application with different media quality from plurality of applications based on determined perceptual quality score for at least one media stream received from each application of the plurality of applications, determining a target perceptual quality score for at least one media stream for at least one candidate application based on the perceptual quality score and network parameters, and harmonizing, at least one media parameter of the at least one media stream received from candidate applications based on the target perceptual quality score.

    METHOD AND ELECTRONIC DEVICE FOR SUPPRESSING NOISE PORTION FROM MEDIA EVENT
    2.
    发明申请
    METHOD AND ELECTRONIC DEVICE FOR SUPPRESSING NOISE PORTION FROM MEDIA EVENT 有权

    公开(公告)号：US20220319528A1

    公开(公告)日：2022-10-06

    申请号：US17716648

    申请日：2022-04-08

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Prasenjit CHAKRABORTY ,  Bhavin SHAH ,  Siddhesh Chandrashekhar GANGAN ,  Vinayak GOYAL ,  Srinidhi N

    IPC: G10L21/0216 ,  G10L21/0232 ,  G10L21/0272

    Abstract: A method for suppressing a noise portion(s) from a media event by an electronic device is provided. The method includes receiving a voice signal comprising the noise portion(s) and a voice(s) during the media event. Further, the method includes determining a weightage(s) for the noise portion(s) throughout the media event. Further, the method includes determining a plurality of parameters associated with the electronic device, where the plurality of parameters comprises at least one of a preference(s) of a user of the electronic device or a current context of the electronic device. Further, the method includes suppressing the noise portion(s) in the voice signal based on the weightage(s) and the plurality of parameters associated with the electronic device. Further, the method includes generating a media file, where the media file includes the voice(s) and non-suppressed noise portion(s).

    APPARATUS AND METHOD FOR ENHANCING VIDEOS
    4.
    发明申请
    APPARATUS AND METHOD FOR ENHANCING VIDEOS 有权

    公开(公告)号：US20210224956A1

    公开(公告)日：2021-07-22

    申请号：US17150800

    申请日：2021-01-15

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Shubham RUSTAGI ,  Sathish CHERUKURI ,  Shashi Kumar PARWANI ,  Mineni Niswanth BABU ,  Prasenjit CHAKRABORTY

    IPC: G06T5/00 ,  G11B27/031 ,  G06K9/00

    Abstract: A computer-implemented method includes obtaining, from a storage, a video to be enhanced, based on a selection of a user; determining corresponding sets of object scores for a plurality of objects identified in the video, respectively, based on a set of predetermined factors; identifying a primary object and one or more secondary objects in the video, among the plurality of objects, based on the corresponding sets of object scores; and applying at least one visual effect to the primary object and at least one secondary object, from the one or more secondary objects, in at least a portion of the video, for obtaining an enhanced video with the at least one visual effect applied at least to the portion of the video.

    METHODS AND SYSTEMS FOR SAVING DATA WHILE STREAMING VIDEO
    6.
    发明申请
    METHODS AND SYSTEMS FOR SAVING DATA WHILE STREAMING VIDEO 有权

    公开(公告)号：US20210127180A1

    公开(公告)日：2021-04-29

    申请号：US16608630

    申请日：2018-05-08

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Prasenjit CHAKRABORTY ,  Om PRAKASH ,  Sachin DEV ,  Shweta AGGARWAL

    IPC: H04N21/845 ,  H04N21/2343 ,  H04N21/2662 ,  H04N21/4402 ,  H04N21/433

    Abstract: Embodiments herein provide methods and systems for saving data while streaming a video. The embodiments include streaming a first fragment of the video at a bit-rate based on network conditions. In an embodiment, the scene content complexity of the first fragment can be analyzed while streaming the first fragment. Based on the screen complexity, the second fragment can be streamed at a bit-rate based on the network conditions and the analyzed screen complexity. In another embodiment, a second fragment can be received at a minimum possible resolution and, thereafter, the scene content complexity of the second fragment can be analyzed while streaming the first fragment. Based on the screen complexity of the second fragment, it can be streamed at a bit-rate based on the network conditions and the analyzed screen complexity. There may be no perceptible difference in streamed quality of the first fragment and the second fragment.

    OPTIMAL SPLIT FEDERATED LEARNING IN WIRELESS NETWORK
    9.
    发明申请
    OPTIMAL SPLIT FEDERATED LEARNING IN WIRELESS NETWORK 有权

    公开(公告)号：US20250013874A1

    公开(公告)日：2025-01-09

    申请号：US18891095

    申请日：2024-09-20

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Jyotirmoy KARJEE ,  Praveen Naik S ,  Srinidhi NAGARAJA RAO ,  Eric Ho Ching YIP ,  Prasenjit CHAKRABORTY ,  Ramesh Babu Venkat DABBIRU

    IPC: G06N3/098

    Abstract: Systems and methods for optimal split federated learning (O-SFL) in a wireless network, including: receiving, by a federal device in the wireless network, local split points associated with a deep neural network (DNN) model over a time period from at least one client device of a plurality of client devices, wherein the plurality of client devices are connected to an edge device for training the DNN model using split federated learning (SFL); determining, by the federal device, an average of the local split points; determining, by the federal device, a global split point for partitioning the DNN model between the at least one client device and the edge device based on the average of the local split points; and applying, by the federal device, the determined global split point to train the DNN model.

Patent Agency Ranking