公开(公告)号：US10102443B1

公开(公告)日：2018-10-16

申请号：US15232941

申请日：2016-08-10

Applicant: Google LLC

Inventor： Qixing Huang ,  Mei Han ,  Bo Wu ,  Sergey Ioffe

IPC: G06K9/46 ,  G06K9/62

Abstract: An image processing system automatically segments and labels an image using a hierarchical classification model. A global classification model determines initial labels for an image based on features of the image. A label-based descriptor is generated based on the initial labels. A local classification model is then selected from a plurality of learned local classification model based on the label-based descriptor. The local classification model is applied to the features of the input image to determined refined labels. The refined labels are stored in association with the input image.

公开(公告)号：US20200090039A1

公开(公告)日：2020-03-19

申请号：US16494842

申请日：2017-11-17

Applicant: Google LLC

Inventor： Yang Song ,  Yuan Li ,  Bo Wu ,  Chao-Yeh Chen ,  Xiao Zhang ,  Hartwig Adam

IPC: G06N3/08 ,  G06N20/00 ,  G06K9/32

Abstract: A computer-implemented method for generating a unified machine learning model using a neural network on a data processing apparatus is described. The method includes the data processing apparatus determining respective learning targets for each of a plurality of object verticals. The data processing apparatus determines the respective learning targets based on two or more embedding outputs of the neural network. The method also includes the data processing apparatus training the neural network to identify data associated with each of the plurality of object verticals. The data processing apparatus trains the neural network using the respective learning targets and based on a first loss function. The data processing apparatus uses the neural network trained to generate a unified machine learning model, where the model is configured to identify particular data items associated with each of the plurality of object verticals.

公开(公告)号：US20240289605A1

公开(公告)日：2024-08-29

申请号：US18173347

申请日：2023-02-23

Applicant: Google LLC

Inventor： Lav Rai ,  Xiang Xu ,  Yen-Min Hsu ,  Bo Wu ,  Daiyi Peng

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: Aspects of the disclosure are directed to proxy task design tools that automatically find proxy tasks, such as optimal proxy tasks, for neural architecture searches. The proxy task design tools can include one or more tools to search for an optimal proxy task having the lowest neural architecture search cost while meeting a minimum correlation requirement threshold after being provided with a proxy task search space definition. The proxy task design tools can further include one or more tools to select candidate models for computing correlation scores of proxy tasks as well as one or more tools to measure variance of a model. The proxy task design tools can minimize time and effort involved in designing the proxy task.

公开(公告)号：US10417992B2

公开(公告)日：2019-09-17

申请号：US15969231

申请日：2018-05-02

Applicant: Google LLC

Inventor： Hayes Solos Raffle ,  David Sparks ,  Bo Wu

IPC: G06F1/00 ,  G09G5/00 ,  G02B27/01 ,  G06F3/01 ,  G06F3/0354 ,  G06F3/044 ,  G09G5/12 ,  G02B27/00

Abstract: Disclosed are methods and devices for varying functionality of a wearable computing device. An example device includes a first sensor and a second sensor. An example method includes, while a device is operating in a first state, receiving an indication of a touch input at the first sensor. The second sensor is configured in an idle mode based on the device operating in the first state. The method further includes, in response to receiving the indication of the touch input, triggering the second sensor to operate in an active mode and receiving data from the second sensor. The method further includes determining, based on the data, whether the device is being worn.

公开(公告)号：US20180254019A1

公开(公告)日：2018-09-06

申请号：US15969231

申请日：2018-05-02

Applicant: Google LLC

Inventor： Hayes Solos Raffle ,  David Sparks ,  Bo Wu

IPC: G09G5/00 ,  G06F3/044 ,  G02B27/01 ,  G06F3/01 ,  G06F3/0354 ,  G09G5/12

CPC classification number: G09G5/006 ,  G02B27/0093 ,  G02B27/01 ,  G02B27/017 ,  G02B2027/0178 ,  G06F3/013 ,  G06F3/0346 ,  G06F3/03547 ,  G06F3/044 ,  G09G5/12 ,  G09G2354/00 ,  G09G2370/06

Abstract: Disclosed are methods and devices for varying functionality of a wearable computing device. An example device includes a first sensor and a second sensor. An example method includes, while a device is operating in a first state, receiving an indication of a touch input at the first sensor. The second sensor is configured in an idle mode based on the device operating in the first state. The method further includes, in response to receiving the indication of the touch input, triggering the second sensor to operate in an active mode and receiving data from the second sensor. The method further includes determining, based on the data, whether the device is being worn.

公开(公告)号：US09972277B2

公开(公告)日：2018-05-15

申请号：US15498278

申请日：2017-04-26

Applicant: Google LLC

Inventor： Hayes Solos Raffle ,  David Sparks ,  Bo Wu

IPC: G06F1/00 ,  G09G5/00 ,  G06F3/044 ,  G09G5/12 ,  G02B27/01 ,  G06F3/0354 ,  G06F3/01

CPC classification number: G09G5/006 ,  G02B27/0093 ,  G02B27/01 ,  G02B27/017 ,  G02B2027/0178 ,  G06F3/013 ,  G06F3/03547 ,  G06F3/044 ,  G09G5/12 ,  G09G2354/00 ,  G09G2370/06

Abstract: Disclosed are methods and devices for varying functionality of a wearable computing device. An example device includes a first sensor and a second sensor. An example method includes, while a device is operating in a first state, receiving an indication of a touch input at the first sensor. The second sensor is configured in an idle mode based on the device operating in the first state. The method further includes, in response to receiving the indication of the touch input, triggering the second sensor to operate in an active mode and receiving data from the second sensor. The method further includes determining, based on the data, whether the device is being worn.