公开(公告)号：US20230410329A1

公开(公告)日：2023-12-21

申请号：US18460338

申请日：2023-09-01

Applicant: Google LLC

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

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

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

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.

公开(公告)号：USD987674S1

公开(公告)日：2023-05-30

申请号：US29825616

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.

公开(公告)号：US11310331B2

公开(公告)日：2022-04-19

申请号：US16719951

申请日：2019-12-18

Applicant: Google LLC

Inventor： Fan Zhang ,  Peng Zhuang ,  Yi Meng

IPC: H04L29/08 ,  G06F3/0484 ,  G06F12/0813 ,  H04W4/60 ,  H04L67/5681 ,  H04L67/306 ,  H04L67/125 ,  H04L67/04

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.

公开(公告)号：US20220076433A1

公开(公告)日：2022-03-10

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 ,  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.

公开(公告)号：USD941341S1

公开(公告)日：2022-01-18

申请号：US29801530

申请日：2021-07-29

Applicant: Google LLC

Designer： Jason Gouliard ,  Sharon Lee ,  Amit Ghorawat ,  Sada Kurapati ,  Fan Zhang

公开(公告)号：USD940735S1

公开(公告)日：2022-01-11

申请号：US29708629

申请日：2019-10-08

Applicant: Google LLC

Designer： Jason Gouliard ,  Sharon Lee ,  Amit Ghorawat ,  Sada Kurapati ,  Fan Zhang

公开(公告)号：US10560546B2

公开(公告)日：2020-02-11

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.

公开(公告)号：US10165071B2

公开(公告)日：2018-12-25

申请号：US14997370

申请日：2016-01-15

Applicant: Google LLC

Inventor： Fan Zhang ,  Joshy Joseph ,  Alexander James Rickabaugh ,  Peng Zhuang

IPC: H04L29/08 ,  G06F11/34

Abstract: This document describes systems, methods, devices, and other techniques for monitoring the performance of activities executed at a computing device. In some implementations, a computing device receives a user input to invoke performance of an activity by the computing device. Multiple portions of computer code associated with the activity can be identified. For each portion of computer code, (i) the respective portion of computer code can be executed, and (ii) data can be recorded about the executing of the respective portion of computer code that indicates a time duration of the executing of the respective portion of computer code. A total time to completion of the activity can be provided based at least in part on aggregating the recorded data about the executing of the multiple portions of computer code.

公开(公告)号：USD989807S1

公开(公告)日：2023-06-20

申请号：US29822801

申请日：2022-01-12

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.

公开(公告)号：US20220206645A1

公开(公告)日：2022-06-30

申请号：US17247914

申请日：2020-12-30

Applicant: Google LLC

Inventor： Gabrielle Zadina ,  Fan Zhang ,  Ahmed Fakhry ,  Gary Hyun Jin Kim ,  Xiyuan Xia

IPC: G06F3/0482 ,  G06F3/0488 ,  H04N21/431

Abstract: A system and method is provided for the operating system level management of screen content capture in a computing device. In response to invoking of screen capture functionality of the device, a screen capture user interface (UI) is generated. The screen capture UI provides for selection of a screen capture mode, including a screenshot mode providing for the capture of still image content, and a screen recording mode providing for the capture of moving image content, or video content, alone or together with audio content. The screen capture UI can also provide for the selection of a screen capture area, including selection of one of a full screen capture area, a tab or window screen capture area, or a custom screen capture area that can be set by the user.