中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

79 records (took 0.032 seconds)

    SUPERVISED LEARNING AND OCCLUSION MASKING FOR OPTICAL FLOW ESTIMATION
    1.
    发明申请
    SUPERVISED LEARNING AND OCCLUSION MASKING FOR OPTICAL FLOW ESTIMATION 审中-公开

    公开(公告)号：WO2022104310A1

    公开(公告)日：2022-05-19

    申请号：PCT/US2021/072062

    申请日：2021-10-27

    Applicant: QUALCOMM INCORPORATED

    Inventor： LIN, Jamie Menjay ,  JEONG, Jisoo ,  PORIKLI, Fatih Murat

    IPC: G06T7/20

    Abstract: Systems and techniques are described for performing supervised learning (e.g., semi-supervised learning, self-supervised learning, and/or mixed supervision learning) for optical flow estimation. For example, a method can include obtaining an image associated with a sequence of images and generating an occluded image. The occluded image can include at least one of the image with an occlusion applied to the image and a different image of the sequence of images with the occlusion applied. The method can include determining a matching map based at least on matching areas of the image and the occluded image and, based on the matching map, determining a loss term associated with an optical flow loss prediction associated with the image and the occluded image. The loss term may include a matched loss and/or other loss. Based on the loss term, the method can include training a network configured to determine an optical flow between images.

    DATA EFFICIENT LEARNING AND RAPID DOMAIN ADAPTATION FOR WIRELESS POSITIONING AND TRACKING
    2.
    发明申请
    DATA EFFICIENT LEARNING AND RAPID DOMAIN ADAPTATION FOR WIRELESS POSITIONING AND TRACKING 审中-公开

    公开(公告)号：WO2022047420A1

    公开(公告)日：2022-03-03

    申请号：PCT/US2021/048541

    申请日：2021-08-31

    Applicant: QUALCOMM INCORPORATED

    Inventor： LIN, Jamie Menjay ,  KWAK, Nojun ,  PORIKLI, Fatih Murat

    IPC: G06N20/20 ,  G06N3/04 ,  G01S5/02

    Abstract: Certain aspects of the present disclosure provide techniques for machine learning using basis decomposition, comprising receiving a first runtime record, where the first runtime record includes RF signal data collected in a physical space; processing the first runtime record using a plurality of basis machine learning (ML) models to generate a plurality of inferences; aggregating the plurality of inferences to generate a prediction comprising a plurality of coordinates; and outputting the prediction, where the plurality of coordinates indicate a location of a physical element in a physical space.

    PHASE SELECTIVE CONVOLUTION WITH DYNAMIC WEIGHT SELECTION
    3.
    发明申请
    PHASE SELECTIVE CONVOLUTION WITH DYNAMIC WEIGHT SELECTION 审中-公开

    公开(公告)号：WO2021097440A1

    公开(公告)日：2021-05-20

    申请号：PCT/US2020/060763

    申请日：2020-11-16

    Applicant: QUALCOMM INCORPORATED

    Inventor： LIN, Jamie Menjay ,  YANG, Yang ,  NOORZAD, Parham

    IPC: G06N3/04 ,  G06N3/08

    Abstract: Aspects described herein provide a method of performing phase selective convolution, including: receiving multi-phase pre-activation activation data; partitioning the multi-phase pre-activation data; applying a first activation function to the set of first phase pre-activation data to form a set of first phase activation output; convolving the set of first phase activation output with a first convolution kernel to form a first phase output feature map; negating the set of second phase activation data; applying a second activation function to the negated set of second phase pre-activation data to form a set of second phase activation output; convolving the set of second phase activation output with a second convolution kernel to form a second phase output feature map; negating the second phase output feature map; and training the neural network based on the first phase output feature map and the second phase output feature map.

    OUTPUTTING OF CODEWORD BITS FOR TRANSMISSION PRIOR TO LOADING ALL INPUT BITS
    4.
    发明申请
    OUTPUTTING OF CODEWORD BITS FOR TRANSMISSION PRIOR TO LOADING ALL INPUT BITS 审中-公开
    在加载所有输入位之前输出传输的码位

    公开(公告)号：WO2018034872A1

    公开(公告)日：2018-02-22

    申请号：PCT/US2017/045596

    申请日：2017-08-04

    Applicant: QUALCOMM INCORPORATED

    Inventor： SARKIS, Gabi ,  YANG, Yang ,  JIANG, Jing ,  LIN, Jamie Menjay ,  SMEE, John Edward

    IPC: H04L1/00

    CPC classification number: H03M13/3761 ,  H03M13/13 ,  H03M13/611 ,  H03M13/6525 ,  H04L1/00 ,  H04L1/0041 ,  H04L1/0057 ,  H04L1/0058

    Abstract: Methods, systems, and devices for outputting of codeword bits for transmission prior to loading all input bits. An example encoder may have multiple encoding branches. The encoder may divide the encoding branches into first and second encoding branch subsets, outputs of the first encoding branch subset being independent of inputs to the second encoding branch subset. The encoder may generate first and second subsets of output bits of a codeword in first and second encoding operations, the generating comprising inputting information bits of an information bit-vector and at least one frozen bit into respective encoding branches of the plurality of encoding branches and generating the first subset of output bits using the first encoding branch subset prior to generating the second subset of output bits using the second encoding branch subset. The encoder may output the first subset of output bits prior to outputting the second subset of output bits.

    Abstract translation: 用于在加载所有输入比特之前输出用于传输的码字比特的方法，系统和设备。 示例编码器可以具有多个编码分支。 编码器可将编码分支划分为第一编码分支子集和第二编码分支子集，第一编码分支子集的输出独立于对第二编码分支子集的输入。 编码器可以在第一编码操作和第二编码操作中生成码字的输出比特的第一子集和第二子集，生成步骤包括将信息比特向量和至少一个冻结比特的信息比特输入到多个编码分支的相应编码分支中， 在使用第二编码分支子集生成输出比特的第二子集之前使用第一编码分支子集来生成输出比特的第一子集。 编码器可以在输出第二输出比特子集之前输出第一输出比特子集。

    CONTROL SIGNALING SUPPORTING MULTI-PRIORITY SCHEDULING
    6.
    发明申请
    CONTROL SIGNALING SUPPORTING MULTI-PRIORITY SCHEDULING 审中-公开
    控制信号支持多重优先级调度

    公开(公告)号：WO2016148841A1

    公开(公告)日：2016-09-22

    申请号：PCT/US2016/018783

    申请日：2016-02-19

    Applicant: QUALCOMM INCORPORATED

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

    IPC: H04W72/14 ,  H04W72/12

    CPC classification number: H04W72/1289 ,  H04W72/1247 ,  H04W72/1273 ,  H04W72/14

    Abstract: The disclosure relates in some aspects to techniques for use in systems where a plurality of devices with different priority levels share a common set of resources for communication (e.g., downlink transmissions). Certain aspects provide a new indication channel and a procedure to signal scheduling information (e.g., priority information). Such information may serve as an indicator for possible new grants. Such information may additionally serve as an indicator for higher-priority scheduling conflicts or include explicit commands that result from conflicts (e.g., conflicts relating to puncturing of resources allocated for transmissions to lower priority devices).

    Abstract translation: 本公开在一些方面涉及用于其中具有不同优先级的多个设备共享用于通信（例如，下行链路传输）的公共资源集合的系统中的技术。 某些方面提供新的指示信道和信号调度信息（例如，优先级信息）的过程。 这些信息可以作为可能的新赠款的指标。 这样的信息可以另外用作更高优先级调度冲突的指示符，或者包括由冲突产生的显式命令（例如，与分配给低优先级设备的传输的资源的删截有关的冲突）。

    VOLUMETRIC SAMPLING WITH CORRELATIVE CHARACTERIZATION FOR DENSE ESTIMATION
    7.
    发明申请
    VOLUMETRIC SAMPLING WITH CORRELATIVE CHARACTERIZATION FOR DENSE ESTIMATION 审中-公开

    公开(公告)号：WO2022260745A1

    公开(公告)日：2022-12-15

    申请号：PCT/US2022/023548

    申请日：2022-04-05

    Applicant: QUALCOMM INCORPORATED

    Inventor： LIN, Jamie Menjay ,  PORIKLI, Fatih Murat

    IPC: G06T7/246 ,  G06T7/269 ,  G06T7/277

    Abstract: Systems and techniques are described herein for performing optical flow estimation for one or more frames. For example, a process can include determining an optical flow prediction associated with a plurality of frames. The process can include determining a position of at least one feature associated with a first frame and determining, based on the position of the at least one feature in the first frame and the optical flow prediction, a position estimate of a search area for searching for the at least one feature in a second frame. The process can include determining, from within the search area, a position of the at least one feature in the second frame.

    CONVOLUTION WITH KERNEL EXPANSION AND TENSOR ACCUMULATION
    8.
    发明申请
    CONVOLUTION WITH KERNEL EXPANSION AND TENSOR ACCUMULATION 审中-公开

    公开(公告)号：WO2022256814A1

    公开(公告)日：2022-12-08

    申请号：PCT/US2022/072709

    申请日：2022-06-02

    Applicant: QUALCOMM INCORPORATED

    Inventor： LIN, Jamie Menjay ,  BHALGAT, Yash Sanjay ,  PARK, Edwin Chongwoo

    IPC: G06N3/04 ,  G06N3/063

    Abstract: Certain aspects of the present disclosure provide techniques for kernel expansion. An input data tensor is received at a first layer in a neural network, and a first convolution is performed for a first kernel, where the first kernel has a size greater than a preferred size. Performing the first convolution comprises generating a plurality of intermediate tensors by performing a plurality of intermediate convolutions using a plurality of intermediate kernels with a size of the preferred size, and accumulating the plurality of intermediate tensors to generate an output tensor for the first convolution.

    CROSS-CORRELATION REDUCTION FOR CONTROL SIGNALS
    9.
    发明申请
    CROSS-CORRELATION REDUCTION FOR CONTROL SIGNALS 审中-公开

    公开(公告)号：WO2019199690A1

    公开(公告)日：2019-10-17

    申请号：PCT/US2019/026380

    申请日：2019-04-08

    Applicant: QUALCOMM INCORPORATED

    Inventor： LIN, Jamie Menjay ,  MALLIK, Siddhartha ,  KADOUS, Tamer

    IPC: H04L1/00 ,  H04J13/00

    Abstract: Methods, systems, and devices for wireless communications are described. In accordance with the described techniques, communicating devices (e.g., an encoder and decoder) may apply an orthogonal cover code to a polar codeword to reduce cross-correlation between different codewords. For example, such techniques may reduce power consumption at a decoding device by providing for earlier decoding termination (e.g., as a result of the reduced cross-correlation). Techniques for generating the cover codes (e.g., on a per-aggregation level basis) and applying the cover codes (e.g., within a search space) are described. Additionally or alternatively, the described techniques may relate to seeding of reference signals used to support decoding of the codewords. Improved orthogonality between reference signal seeds may further suppress codeword recipient ambiguity.

    PUNCTURE RECOVERY AND RESOURCE RECLAIMING FOR MULTI-PRIORITY SCHEDULING
    10.
    发明申请
    PUNCTURE RECOVERY AND RESOURCE RECLAIMING FOR MULTI-PRIORITY SCHEDULING 审中-公开
    针对多优先调度的抢回恢复和资源回收

    公开(公告)号：WO2018075899A1

    公开(公告)日：2018-04-26

    申请号：PCT/US2017/057603

    申请日：2017-10-20

    Applicant: QUALCOMM INCORPORATED

    Inventor： LIN, Jamie Menjay ,  XU, Hao ,  LI, Chong ,  LI, Chih-Ping ,  JIANG, Jing ,  JI, Tingfang

    IPC: H04W72/14 ,  H04W72/12

    Abstract: Various techniques provide for identifying and transmitting a first transmission to a UE in a first transmission time interval (TTI), and puncturing a portion of the first transmission with a higher priority second transmission that has a shorter TTI than the first TTI. The punctured portion of the first transmission may then be transmitted in a subsequent portion of the first TTI, concurrently with an originally allocated portion of the first transmission for that subsequent portion of the TTI. A UE may identify the punctured portion of the first transmission, and identify that the punctured portion of the first transmission is being transmitted in the subsequent portion of the first TTI. The UE may decode the received transmissions and merge the punctured portion with other, non-punctured, portions of the first transmission.

    Abstract translation: 各种技术提供了在第一传输时间间隔（TTI）中识别并向UE发送第一传输，并且利用具有较短TTI的较高优先级第二传输来穿孔第一传输的一部分 比第一个TTI。 第一传输的收缩部分然后可以在第一TTI的后续部分中与用于TTI的后续部分的第一传输的原始分配部分同时发送。 UE可以识别第一传输的收缩部分，并识别第一传输的收缩部分正在第一TTI的后续部分中传输。 UE可以对接收到的传输进行解码并且将收缩部分与第一传输的其他非收缩部分合并。

Patent Agency Ranking