中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

44 records (took 0.021 seconds)

    SYSTEMS AND METHODS FOR CONTROLLING VIRTUAL WIDGETS IN GESTURE-CONTROLLED DEVICE
    1.
    发明申请
    SYSTEMS AND METHODS FOR CONTROLLING VIRTUAL WIDGETS IN GESTURE-CONTROLLED DEVICE 审中-公开

    公开(公告)号：WO2022247506A1

    公开(公告)日：2022-12-01

    申请号：PCT/CN2022/086621

    申请日：2022-04-13

    Applicant: HUAWEI TECHNOLOGIES CO.,LTD.

    Inventor： HOSSEINKHANI LOORAK, Mona ,  ZHOU, Wei ,  SINGH, Gaganpreet ,  YI, Xiu ,  LI, Wei

    IPC: G06F3/01

    Abstract: A gesture-controlled device and a method thereon are provided. The method includes capturing a plurality of video frames of a user's body and processing the plurality of video frames to allow detecting a portion of the user's body and to allow recognizing hand gestures. In response to detecting the portion of the user's body, the method includes generating at least one widget interaction region corresponding to the portion of the user's body. The method further includes recognizing, a mid-air hand gesture in the at least one widget interaction region, mapping the mid-air hand gesture to at least one virtual widget on the gesture-controlled device, and manipulating the at least one virtual widget based on the mid-air hand gesture. The method and device allow manipulation of virtual widgets using mid-air gestures on a gesture-controlled device.

    USING A TOUCH INPUT TOOL TO MODIFY CONTENT RENDERED ON TOUCHSCREEN DISPLAYS
    4.
    发明申请
    USING A TOUCH INPUT TOOL TO MODIFY CONTENT RENDERED ON TOUCHSCREEN DISPLAYS 审中-公开

    公开(公告)号：WO2021223536A1

    公开(公告)日：2021-11-11

    申请号：PCT/CN2021/082822

    申请日：2021-03-24

    Applicant: HUAWEI TECHNOLOGIES CO., LTD.

    Inventor： LI, Wei ,  LI, Jun ,  XU, Qiang ,  LI, Chenhe ,  SUN, Junwei ,  SINGH, Gaganpreet

    IPC: G06F3/033

    Abstract: A method is provided including generating touch coordinate information corresponding to touch interactions with a touchscreen display of an electronic device and updating information rendered on the touchscreen display in response to determining that the touch coordinate information matches a tool shaft movement gesture corresponding to movement of a touch tool shaft over an area of the touchscreen display. A device is provided, including a touchscreen display comprising a display and a touch sensing system configured to generate signals corresponding to screen touches of the display, a processing device operatively coupled to the touchscreen display, and a non-transitory memory coupled to the processing device and storing software instructions that when executed by the processing device configure the processing device to carry out the provided method. The ability to process tool shaft gestures may improve one or both of the operation of the device and the user experience with the device.

    METHODS AND SYSTEMS FOR TRAINING CONVOLUTIONAL NEURAL NETWORK USING BUILT-IN ATTENTION
    5.
    发明申请
    METHODS AND SYSTEMS FOR TRAINING CONVOLUTIONAL NEURAL NETWORK USING BUILT-IN ATTENTION 审中-公开

    公开(公告)号：WO2021093794A1

    公开(公告)日：2021-05-20

    申请号：PCT/CN2020/128232

    申请日：2020-11-12

    Applicant: HUAWEI TECHNOLOGIES CO., LTD.

    Inventor： QUADER, Niamul ,  KHALIL, Md Ibrahim ,  LU, Juwei ,  DAI, Peng ,  LI, Wei

    IPC: G06N3/04

    Abstract: Methods and systems for updating the weights of a set of convolution kernels of a convolutional layer of a neural network are described. A set of convolution kernels having attention-infused weights is generated by using an attention mechanism based on characteristics of the weights. For example, a set of location-based attention multipliers is applied to weights in the set of convolution kernels, a magnitude-based attention function is applied to the weights in the set of convolution kernels, or both. An output activation map is generated using the set of convolution kernels with attention-infused weights. A loss for the neural network is computed, and the gradient is back propagated to update the attention-infused weights of the convolution kernels.

    METHOD AND SYSTEM FOR IMAGE SEARCH AND CROPPING
    6.
    发明申请
    METHOD AND SYSTEM FOR IMAGE SEARCH AND CROPPING 审中-公开

    公开(公告)号：WO2020248866A1

    公开(公告)日：2020-12-17

    申请号：PCT/CN2020/093831

    申请日：2020-06-02

    Applicant: HUAWEI TECHNOLOGIES CO., LTD.

    Inventor： RAO, Varshanth Ravindra ,  AHMAD, Uzair ,  DAI, Peng ,  LU, Juwei ,  LI, Wei ,  XU, Jianpeng

    IPC: G06K9/62

    Abstract: Methods and systems for processing an image are described. A saliency map is generated from the image. The saliency map indicates one or more salient portions of the image that have saliency values satisfying a saliency criterion. A scene graph is generated for at least the one or more salient portions. The scene graph represents a plurality of objects detected in the image. The scene graph further represents one or more relationships between each respective object pairs. One or more dataset entries associated with the image are generated. Each of the one or more relationships for each of the one or more object pairs is indicated by a respective dataset entry. The one or more dataset entries are stored in a first dataset.

    METHODS, DEVICES, AND MEDIA FOR MANAGING A VIRTUAL WORKSPACE
    7.
    发明申请
    METHODS, DEVICES, AND MEDIA FOR MANAGING A VIRTUAL WORKSPACE 审中-公开

    公开(公告)号：WO2023071737A1

    公开(公告)日：2023-05-04

    申请号：PCT/CN2022/124063

    申请日：2022-10-09

    Applicant: HUAWEI TECHNOLOGIES CO., LTD.

    Inventor： LI, Wei ,  YAN, Che ,  HUANG, Dayuan

    IPC: H04L12/18

    Abstract: Methods, devices, and processor-readable media for managing a virtual workspace shared by multiple devices are described. A unified GUI is presented to each device in which the other devices sharing the virtual workspace are represented by GUI elements, with the location of the other local devices present within the same local environment corresponding to a display location of the corresponding GUI element around the perimeter of the GUI screen. The locations of the other local devices are determined based on sensor data from the local devices, such as NFC radio data or other short-range sensor data, without the need for a dedicated, specially positioned camera or other sensor configured to track the devices within the local environment.

    SYSTEMS AND METHODS FOR PREDICTION-BASED DRIVER ASSISTANCE
    8.
    发明申请
    SYSTEMS AND METHODS FOR PREDICTION-BASED DRIVER ASSISTANCE 审中-公开

    公开(公告)号：WO2023061363A1

    公开(公告)日：2023-04-20

    申请号：PCT/CN2022/124625

    申请日：2022-10-11

    Applicant: HUAWEI TECHNOLOGIES CO., LTD.

    Inventor： KHAN, Taslim Arefin ,  FAN, Szu Wen ,  LI, Wei

    IPC: G08G1/01

    Abstract: A system and method for providing driver assistance are provided. The method comprises: a current vehicle state of a vehicle (105) at a current time step and an environment map representing an environment of the vehicle (105) at least at the current time step are obtained. Augmented reality feedback is generated including a virtual vehicle representing a predicted future vehicle state, where the predicted future vehicle state is predicted for a given future time step based on at least one of the current vehicle state or the current environment. The generated augmented reality feedback including the virtual vehicle is outputted to be displayed by a display device (136).

    METHODS, DEVICES, AND COMPUTER-READABLE STORAGE MEDIA FOR PERFORMING FUNCTION BASED ON USER INPUT
    9.
    发明申请
    METHODS, DEVICES, AND COMPUTER-READABLE STORAGE MEDIA FOR PERFORMING FUNCTION BASED ON USER INPUT 审中-公开

    公开(公告)号：WO2022247511A1

    公开(公告)日：2022-12-01

    申请号：PCT/CN2022/086888

    申请日：2022-04-14

    Applicant: HUAWEI TECHNOLOGIES CO., LTD.

    Inventor： HUANG, Da-Yuan ,  LUO, Wenshu ,  YAN, Che ,  LI, Wei

    IPC: G06F3/0488

    Abstract: There is described a method performed by a computing device having first and second touch-sensitive user interfaces. According to this method, when a user input is applied to one of the first and second user interfaces, the computing device detects the user input and determines a force applied by the user input and a type of the user input. The computing device then determines whether to perform a function such as whether to display a virtual trackpad or a virtual keyboard, based on the force, the type of the user input, and a determination whether the user input is applied to a selected one of the first and second user interfaces.

Patent Agency Ranking