中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

28 records (took 0.014 seconds)

    Scalable Real-Time Hand Tracking
    11.
    发明申请
    Scalable Real-Time Hand Tracking 有权

    公开(公告)号：US20210174519A1

    公开(公告)日：2021-06-10

    申请号：US16709128

    申请日：2019-12-10

    Applicant: Google LLC

    Inventor： Valentin Bazarevsky ,  Fan Zhang ,  Andrei Vakunov ,  Andrei Tkachenka ,  Matthias Grundmann

    IPC: G06T7/246 ,  G06T7/73 ,  G06K9/00

    Abstract: Example aspects of the present disclosure are directed to computing systems and methods for hand tracking using a machine-learned system for palm detection and key-point localization of hand landmarks. In particular, example aspects of the present disclosure are directed to a multi-model hand tracking system that performs both palm detection and hand landmark detection. Given a sequence of image frames, for example, the hand tracking system can detect one or more palms depicted in each image frame. For each palm detected within an image frame, the machine-learned system can determine a plurality of hand landmark positions of a hand associated with the palm. The system can perform key-point localization to determine precise three-dimensional coordinates for the hand landmark positions. In this manner, the machine-learned system can accurately track a hand depicted in the sequence of images using the precise three-dimensional coordinates for the hand landmark positions.

    OPTIMIZING USER INTERFACE DATA CACHING FOR FUTURE ACTIONS
    12.
    发明申请
    OPTIMIZING USER INTERFACE DATA CACHING FOR FUTURE ACTIONS 审中-公开

    公开(公告)号：US20190281128A1

    公开(公告)日：2019-09-12

    申请号：US16426672

    申请日：2019-05-30

    Applicant: Google LLC

    Inventor： Fan Zhang ,  Peng Zhuang ,  Yi Meng

    IPC: H04L29/08 ,  G06F3/0484 ,  G06F12/0813 ,  H04W4/60

    Abstract: The subject matter of this specification generally relates to pre-caching data for a predicted future action. In some implementations, a client device includes a data storage device having a cache that stores data received for one or more mobile applications and a data processing apparatus that communicates with the data storage device and a display. A user interface context can be determined for a given user interface being presented for a given application. A predicted next action that a user of the client device will perform at the given user interface can be determined based on the user interface context. Prior to detecting the predicted next action, a request for next action data that will be presented in response to the user performing the predicted next action can be transmitted over a network. The next action data can be received and stored in the cache.

    SEGMENTING AND CLASSIFYING UNSTRUCTURED TEXT USING MULTI-TASK NEURAL NETWORKS
    13.
    发明公开
    SEGMENTING AND CLASSIFYING UNSTRUCTURED TEXT USING MULTI-TASK NEURAL NETWORKS 审中-公开

    公开(公告)号：US20240111999A1

    公开(公告)日：2024-04-04

    申请号：US18375960

    申请日：2023-10-02

    Applicant: Google LLC

    Inventor： Itay Laish ,  Amir Reuven Feder ,  Fan Zhang ,  Ayelet Benjamini

    IPC: G06N3/0455 ,  G06N3/048

    CPC classification number: G06N3/0455 ,  G06N3/048

    Abstract: A multi-task neural network system is described. The system includes a shared neural network configured to receive as input a text span from a clinical note, and for each of one or more text segments in the text span, processing the text segment to generate a set of text segment embeddings. The system further includes a segmentation neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to determine whether the text segment is a section title or not. The system further includes a section type classification neural network configured to, for each of the one or more text segments, process the respective set of text segment embeddings to classify the text segment into a section type of a plurality of section types.

    Display screen or portion thereof with transitional graphical user interface
    14.
    外观设计
    Display screen or portion thereof with transitional graphical user interface 有权

    公开(公告)号：USD989123S1

    公开(公告)日：2023-06-13

    申请号：US29825619

    申请日：2022-02-03

    Applicant: Google LLC

    Designer： Jennifer Cordova ,  Jason Gouliard ,  Dylan Taffe ,  Fan Zhang ,  Jawwad Wasti ,  Amit Ghorawat ,  Madeline Chan ,  Zhen Wang

    Abstract: FIG. 1 is a front view of a first image in a sequence according to our design for a display screen or portion thereof with transitional graphical user interface;
    FIG. 2 is a front view of a second image in the sequence thereof; and,
    FIG. 3 is a front view of a third image in the sequence thereof.
    The appearance of the transitional image transitions between the images shown in FIGS. 1-3. The process or period in which one image transitions to another forms no part of the claimed design.
    The outer broken line rounded rectangles showing a device, the broken line rectangle showing the display screen or portion thereof, and all other broken lines showing portions of the graphical user interface form no part of the claimed design.

    Scalable real-time hand tracking
    17.
    发明授权
    Scalable real-time hand tracking 有权

    公开(公告)号：US11783496B2

    公开(公告)日：2023-10-10

    申请号：US17527463

    申请日：2021-11-16

    Applicant: Google LLC

    Inventor： Valentin Bazarevsky ,  Fan Zhang ,  Andrei Vakunov ,  Andrei Tkachenka ,  Matthias Grundmann

    IPC: G06T7/246 ,  G06T7/73 ,  G06V40/20

    CPC classification number: G06T7/251 ,  G06T7/75 ,  G06V40/28 ,  G06T2207/20081 ,  G06T2207/30196

    Abstract: Example aspects of the present disclosure are directed to computing systems and methods for hand tracking using a machine-learned system for palm detection and key-point localization of hand landmarks. In particular, example aspects of the present disclosure are directed to a multi-model hand tracking system that performs both palm detection and hand landmark detection. Given a sequence of image frames, for example, the hand tracking system can detect one or more palms depicted in each image frame. For each palm detected within an image frame, the machine-learned system can determine a plurality of hand landmark positions of a hand associated with the palm. The system can perform key-point localization to determine precise three-dimensional coordinates for the hand landmark positions. In this manner, the machine-learned system can accurately track a hand depicted in the sequence of images using the precise three-dimensional coordinates for the hand landmark positions.

    Display screen or portion thereof with transitional graphical user interface
    18.
    外观设计
    Display screen or portion thereof with transitional graphical user interface 有权

    公开(公告)号：USD987679S1

    公开(公告)日：2023-05-30

    申请号：US29824801

    申请日：2022-01-27

    Applicant: Google LLC

    Designer： Jennifer Cordova ,  Jason Gouliard ,  Dylan Taffe ,  Fan Zhang ,  Jawwad Wasti ,  Amit Ghorawat ,  Madeline Chan ,  Zhen Wang

    Abstract: FIG. 1 is a front view of a first image in a sequence according to our design for a display screen or portion thereof with transitional graphical user interface;
    FIG. 2 is a front view of a second image in the sequence thereof; and,
    FIG. 3 is a front view of a third image in the sequence thereof.
    The appearance of the transitional image transitions between the images shown in FIGS. 1-3. The process or period in which one image transitions to another forms no part of the claimed design. The shading depicts a contrast of appearance and is a part of the claimed design.
    The outer broken line rounded rectangles showing a device, the broken line rectangle showing the display screen or portion thereof, and all other broken lines showing portions of the graphical user interface form no part of the claimed design.

    Optimizing geographic region selection
    19.
    发明授权
    Optimizing geographic region selection 有权

    公开(公告)号：US11651038B2

    公开(公告)日：2023-05-16

    申请号：US16347358

    申请日：2018-05-30

    Applicant: Google LLC

    Inventor： Fan Zhang ,  Nicolas H. Remy ,  Anne-Claire Haury

    IPC: G06F16/909 ,  G06F16/9035 ,  G01C21/32 ,  G06F16/901 ,  G01C21/36

    CPC classification number: G06F16/909 ,  G01C21/32 ,  G01C21/3644 ,  G06F16/901 ,  G06F16/9035

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for obtaining i) historical location data specifying geographic locations of the user over a period of time that is included in a user profile of the user and ii) predefined geographic location data specifying a predefined geographic location of the user that is included in the user profile of the user; identifying a pair of cross-contaminated geographic regions that both include geographic locations specified by the historical location data of the user profiles for each of a threshold number of users of the plurality of users, and in response, merging the pair of cross-contaminated geographic regions to define a merged geographic region; and merging the merged geographic region with additional geographic regions until a cross-contamination between a resulting merged geographic region created by the merging and other geographic regions is reduced to a specified level of cross-contamination.

Patent Agency Ranking