知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

21 records (took 0.019 seconds)

    METHOD FOR OUTPUTTING, COMPUTER-READABLE RECORDING MEDIUM STORING OUTPUT PROGRAM, AND OUTPUT DEVICE
    4.
    发明申请
    METHOD FOR OUTPUTTING, COMPUTER-READABLE RECORDING MEDIUM STORING OUTPUT PROGRAM, AND OUTPUT DEVICE 有权

    公开(公告)号：US20220237263A1

    公开(公告)日：2022-07-28

    申请号：US17719438

    申请日：2022-04-13

    Applicant: FUJITSU LIMITED

    Inventor： Moyuru YAMADA

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

    Abstract: A method includes: correcting a vector of a first modal by using a correlation between the vector of the first modal and a vector of a second modal different from the first modal; correcting the vector of the second modal by using the correlation between the vector of the first modal and the vector of the second modal; generating a first vector by using a correlation of two different types of vectors obtained from the corrected vector of the first modal; generating a second vector by using the correlation of the two different types of vectors obtained from the corrected vector of the second modal; generating a third vector in which the first and second vectors are aggregated by using the correlation of the two different types of vectors obtained from a combined vector including a predetermined vector, the generated first and second vectors; and outputting the generated third vector.

    METHOD OF GENERATING AN IMAGE
    5.
    发明申请
    METHOD OF GENERATING AN IMAGE 有权

    公开(公告)号：US20250104291A1

    公开(公告)日：2025-03-27

    申请号：US18813102

    申请日：2024-08-23

    Applicant: Fujitsu Limited

    Inventor： Moyuru YAMADA

    IPC: G06T11/00 ,  G06F3/04845 ,  G06T5/70

    Abstract: A computer-implemented method for generating an image involves receiving input text and layout information, decomposing the text into global and local features, and encoding these features into vectors. The method initializes an initial image representation and uses a trained neural network to predict global noise from the global vector and initial image representation. It also predicts initial local noise for each local feature using their respective vectors and the initial image representation. The final local noise for each feature is determined using the initial local noise and the global noise. The predicted global and final local noises are combined based on the layout information. Finally, the initial image representation is denoised using this combined noise to produce the next image representation, ultimately generating the image.

    STORAGE MEDIUM, INFORMATION PROCESSING APPARATUS, AND DETERMINATION MODEL GENERATION METHOD
    6.
    发明申请
    STORAGE MEDIUM, INFORMATION PROCESSING APPARATUS, AND DETERMINATION MODEL GENERATION METHOD 有权

    公开(公告)号：US20220215203A1

    公开(公告)日：2022-07-07

    申请号：US17502290

    申请日：2021-10-15

    Applicant: FUJITSU LIMITED

    Inventor： Moyuru YAMADA

    IPC: G06K9/62

    Abstract: A non-transitory computer-readable storage medium storing a determination model generation program that causes at least one computer to execute a process, the process includes generating, based on first training data in which image data and character string data that corresponds to the image data are associated with each other, second training data by replacing one of data included in the first training data selected from the image data and the character string data with another data; and generating, by using the first training data and the second training data as input data, a determination model that outputs information that indicates which training data selected from the first training data and the second training data is training data in which correspondence between the image data and the character string data is correct.

    INPUT DEVICE THAT IS WORN BY USER AND INPUT METHOD
    8.
    发明申请
    INPUT DEVICE THAT IS WORN BY USER AND INPUT METHOD 有权
    用户输入的输入设备和输入方法

    公开(公告)号：US20150193014A1

    公开(公告)日：2015-07-09

    申请号：US14559018

    申请日：2014-12-03

    Applicant: FUJITSU LIMITED

    Inventor： Moyuru YAMADA

    IPC: G06F3/033

    CPC classification number: G06F1/1615 ,  G06F1/163 ,  G06F1/1694 ,  G06F3/017

    Abstract: An input device, that is worn on a portion of a user's body, includes: a sensor unit configured to obtain angular velocities and an acceleration in a first coordinate system fixed in the input device; a reference posture specification unit configured to generate a second coordinate system for a reference posture of the user; a rotation matrix calculator configured to calculate a rotation matrix that transforms the angular velocities in the first coordinate system into angular velocities in the second coordinate system using the acceleration in the first coordinate system; a characteristic value calculator configured to calculate characteristic values in the second coordinate system using the angular velocities in the second coordinate system; a command specification unit configured to specify a command according to the characteristic values; and a transmitter configured to transmit the command to the controller.

    Abstract translation: 佩戴在用户身体的一部分上的输入装置包括：传感器单元，被配置为获得固定在输入装置中的第一坐标系中的角速度和加速度; 参考姿势指定单元，被配置为生成用于所述用户的参考姿势的第二坐标系; 旋转矩阵计算器，被配置为计算使用第一坐标系中的加速度将第一坐标系中的角速度转换为第二坐标系中的角速度的旋转矩阵; 特征值计算器，被配置为使用所述第二坐标系中的角速度来计算所述第二坐标系中的特征值; 命令指定单元，被配置为根据所述特征值来指定命令; 以及被配置为将该命令发送到控制器的发射机。

    OBJECT DETECTION DEVICE AND METHOD
    9.
    发明公开
    OBJECT DETECTION DEVICE AND METHOD 审中-公开

    公开(公告)号：US20230290104A1

    公开(公告)日：2023-09-14

    申请号：US18172765

    申请日：2023-02-22

    Applicant: Fujitsu Limited

    Inventor： Moyuru YAMADA

    IPC: G06V10/22 ,  G06V20/50 ,  G06V10/75

    CPC classification number: G06V10/235 ,  G06V20/50 ,  G06V10/751 ,  G06V2201/07 ,  G06V2201/10

    Abstract: An object detection device includes a processor that executes a procedure. The procedure includes: converting an input image into a first vector such that information related to an area of an object in the image is contained in the first vector; converting input text into a second vector such that information related to an order of appearance in the text of one or more word strings each indicating a detection target object included in the text is contained in the second vector; generating a third vector in which the first vector and the second vector have been reflected in a vector of initial values corresponding to detection target objects; and estimating whether or not a feature indicated by the third vector corresponds to a detection target object that appears at which number place in the text, and estimating a position of the detection target object in the image.

    METHOD FOR OUTPUTTING, COMPUTER-READABLE RECORDING MEDIUM STORING OUTPUT PROGRAM, AND OUTPUT DEVICE
    10.
    发明申请
    METHOD FOR OUTPUTTING, COMPUTER-READABLE RECORDING MEDIUM STORING OUTPUT PROGRAM, AND OUTPUT DEVICE 有权

    公开(公告)号：US20220237421A1

    公开(公告)日：2022-07-28

    申请号：US17719211

    申请日：2022-04-12

    Applicant: FUJITSU LIMITED

    Inventor： Moyuru YAMADA

    IPC: G06K9/62 ,  G06N20/00

    Abstract: A computer-implemented outputting method including: generating a correction vector that corrects a vector based on information of a first modal on the basis of correlation between the vector based on the information of the first modal and a vector based on information of a second modal; combining the generated correction vector with the vector based on the information of the first modal; compressing the combined vector based on the information of the first modal according to a predetermined rule; performing normalization processing for the compressed vector based on the information of the first modal; and outputting a vector obtained by the normalization processing.

Patent Agency Ranking