Robyn E Dunn

US Patent:

20220408014, Dec 22, 2022

Filed:

May 11, 2022

Appl. No.:

17/662915

Inventors:

- Redmond WA, US
Donghee Pi - Bellevue WA, US
Robyn E. Dunn - Seattle WA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

H04N 5/232
G06N 20/00

Abstract:

A machine learning (ML) operating mode is selected for a camera. A physical orientation of a housing of a camera is determined. In response to determining the orientation, an operating mode from a set of operating modes is selected. The set of operating modes includes at least a ML inference mode and a ML training mode. Based on the selected operating mode, images obtained by an image capturing unit are processed. In the ML inference mode, a ML controller applies a ML model to the images to infer or predict characteristics of the image (e.g., detecting objects within the images). In the ML training mode, the ML controller is configured to cause a ML model to be trained using images captured by the image capturing unit, either local to the camera or on a remotely located computing device.

US Patent:

20210289131, Sep 16, 2021

Filed:

Mar 16, 2020

Appl. No.:

16/820221

Inventors:

- Redmond WA, US
Donghee Pi - Bellevue WA, US
Robyn E. Dunn - Seattle WA, US

International Classification:

H04N 5/232
G06N 20/00

Abstract:

A machine learning (ML) operating mode is selected for a camera. A physical orientation of a housing of a camera is determined. In response to determining the orientation, an operating mode from a set of operating modes is selected. The set of operating modes includes at least a ML inference mode and a ML training mode. Based on the selected operating mode, images obtained by an image capturing unit are processed. In the ML inference mode, a ML controller applies a ML model to the images to infer or predict characteristics of the image (e.g., detecting objects within the images). In the ML training mode, the ML controller is configured to cause a ML model to be trained using images captured by the image capturing unit, either local to the camera or on a remotely located computing device.

US Patent:

20180307390, Oct 25, 2018

Filed:

Apr 19, 2017

Appl. No.:

15/491781

Inventors:

- Redmond WA, US
Ross N. LUENGEN - Sammamish WA, US
Scott James KRIEDER - Kirkland WA, US
Michael John PATTEN - Sammamish WA, US
Robyn Elizabeth DUNN - Seattle WA, US
Brian Eric UPHOFF - Seattle WA, US
Christopher DOAN - Seattle WA, US
Darren Christopher LAYBOURN - Bellevue WA, US
Phoi Heng LEW - Mill Creek WA, US

Assignee:

Microsoft Technology Licensing, LLC - Redmond WA

International Classification:

G06F 3/0483
G06F 3/0481
G06F 3/0482

Abstract:

Techniques for a contextual new tab experience in a heterogeneous tab environment are described. In at least some implementations, relevant content associated with a user's current task is determined based on contextual information collected from tabs presented in a heterogeneous tab environment. According to various implementations, a new tab is launched displaying the relevant content in the heterogeneous tab environment. Thus, contextually relevant content can be determined from a current task and displayed in a single location via a heterogeneous tab environment.