知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

46 records (took 0.025 seconds)

    PERSONAL DEVICE SENSING BASED ON MULTIPATH MEASUREMENTS
    11.
    发明公开
    PERSONAL DEVICE SENSING BASED ON MULTIPATH MEASUREMENTS 审中-公开

    公开(公告)号：US20240103119A1

    公开(公告)日：2024-03-28

    申请号：US17934598

    申请日：2022-09-23

    Applicant: QUALCOMM Incorporated

    Inventor： Jamie Menjay LIN ,  Tong TANG

    IPC: G01S5/02 ,  G06N3/04 ,  G06N3/08

    CPC classification number: G01S5/0278 ,  G06N3/0472 ,  G06N3/08

    Abstract: Certain aspects of the present disclosure provide techniques for training and using machine learning models to predict locations of stationary and non-stationary objects in a spatial environment. An example method generally includes measuring, by a device, a plurality of signals within a spatial environment. Timing information is extracted from the measured plurality of signals. Based on a machine learning model, the measured plurality of signals within the spatial environment, and the extracted timing information, locations of stationary reflection points and locations of non-stationary reflection points in the spatial environment are predicted. One or more actions are taken by the device based on predicting the locations of stationary reflection points and non-stationary reflection points in the spatial environment.

    MESSAGE EMBEDDING AND EMULATION IN ENTROPY ENCODER-DECODER NETWORKS
    12.
    发明公开
    MESSAGE EMBEDDING AND EMULATION IN ENTROPY ENCODER-DECODER NETWORKS 审中-公开

    公开(公告)号：US20230300097A1

    公开(公告)日：2023-09-21

    申请号：US18184419

    申请日：2023-03-15

    Applicant: QUALCOMM Incorporated

    Inventor： Jamie Menjay LIN

    IPC: H04L51/21 ,  H04L41/16

    CPC classification number: H04L51/21 ,  H04L41/16 ,  H04W4/12

    Abstract: Certain aspects of the present disclosure provide techniques and apparatus for messaging in a wireless communications system using neural networks. An example method generally includes receiving a first message and a second message, wherein the second message comprises a secret message to be hidden in the first message. The first message and second message are combined into a combined message. An emulation message is generated through an encoder neural network based on the combined message. The emulation message generally comprises a message decodable by a receiving device into the first message. The emulation message is output emulation message for transmission to the receiving device.

    SPARSE OPTICAL FLOW ESTIMATION
    15.
    发明申请
    SPARSE OPTICAL FLOW ESTIMATION 有权

    公开(公告)号：US20220101539A1

    公开(公告)日：2022-03-31

    申请号：US17481047

    申请日：2021-09-21

    Applicant: QUALCOMM Incorporated

    Inventor： Jamie Menjay LIN ,  Fatih Murat PORIKLI

    IPC: G06T7/269 ,  G01P13/00 ,  G06T7/246

    Abstract: Systems and techniques are described herein for performing optical flow estimation between one or more frames. For example, a process can include determining a subset of pixels of at least one of a first frame and a second frame, and generating a mask indicating the subset of pixels. The process can include determining, based on the mask, one or more features associated with the subset of pixels of at least the first frame and the second frame. The process can include determining optical flow vectors between the subset of pixels of the first frame and corresponding pixels of a second frame. The process can include generating an optical flow map for the second frame using the optical flow vectors.

    STRUCTURED CONVOLUTIONS AND ASSOCIATED ACCELERATION
    16.
    发明申请
    STRUCTURED CONVOLUTIONS AND ASSOCIATED ACCELERATION 有权

    公开(公告)号：US20210374537A1

    公开(公告)日：2021-12-02

    申请号：US17336048

    申请日：2021-06-01

    Applicant: QUALCOMM Incorporated

    Inventor： Yash Sanjay BHALGAT ,  Fatih Murat PORIKLI ,  Jamie Menjay LIN

    IPC: G06N3/08 ,  G06F17/15 ,  G06F17/16 ,  G06N3/04

    Abstract: Certain aspects of the present disclosure provide techniques for performing machine learning, including generating a set of basis masks for a convolution layer of a machine learning model, wherein each basis mask comprises a binary mask; determining a set of scaling factors, wherein each scaling factor of the set of scaling factors corresponds to a basis mask in the set of basis masks; generating a composite kernel based on the set of basis masks and the set of scaling factors; and performing a convolution operation based on the composite kernel.

    MULTI-CAST RESOURCE ALLOCATION BY AGGREGATION LEVEL
    18.
    发明申请
    MULTI-CAST RESOURCE ALLOCATION BY AGGREGATION LEVEL 审中-公开

    公开(公告)号：US20170230154A1

    公开(公告)日：2017-08-10

    申请号：US15266836

    申请日：2016-09-15

    Applicant: QUALCOMM Incorporated

    Inventor： Saurabha TAVILDAR ,  Jamie Menjay LIN ,  Jing JIANG ,  Tingfang JI

    IPC: H04L5/00 ,  H04W72/04

    CPC classification number: H04L5/0037 ,  H04L5/0046 ,  H04W72/042 ,  H04W72/121

    Abstract: Multicasting resource allocation information per aggregation level is enabled. A device allocates resources to UEs according to aggregation level. At each level, a control message includes a bitmap, where each bit corresponds to a different resource, an array, and an ID field for dynamic mapping to the bitmap. The placement order value of an ID in the field is stored at locations in the array. The index value for those locations in the array identifies which asserted bits in the bitmap correspond to the resource allocation for a UE at the level. The control message is multicast to the UEs specified at the aggregation level. The bitmap may have the same length at each level, or have reducing length at lower levels with the removal of bits already asserted at higher levels. The UE reconstructs the bitmap from the higher level bitmaps and the bitmap for the current level.

    SYSTEMS AND METHODS FOR RECURSIVE DIMENSIONAL DECOMPOSITION CONVOLUTION
    20.
    发明申请
    SYSTEMS AND METHODS FOR RECURSIVE DIMENSIONAL DECOMPOSITION CONVOLUTION 有权

    公开(公告)号：US20250095281A1

    公开(公告)日：2025-03-20

    申请号：US18467451

    申请日：2023-09-14

    Applicant: QUALCOMM Incorporated

    Inventor： Jamie Menjay LIN ,  Kai WANG

    IPC: G06T15/20

    Abstract: Dimensional decomposition convolution systems and techniques are described. A system receives a tensor including a first number of dimensions. The system processes a variant of the tensor using a convolution function including a second number of dimensions to generate a processed tensor. The first number of dimensions is greater than the second number of dimensions. A plurality of dimensions from the first number of dimensions of the tensor are grouped into a dimension of the variant of the tensor to reduce dimensionality of the variant of the tensor to the second number of dimensions.

Patent Agency Ranking