Brian J Price

US Patent:

8099429, Jan 17, 2012

Filed:

Dec 11, 2006

Appl. No.:

11/608878

Inventors:

Roderic C. Deyo - Redmond WA, US
Sandeep Sahasrabudhe - Kirkland WA, US
Sunil Swami - Sammamish WA, US
Brian D. Price - Everett WA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

G06F 17/30
G06F 7/00

US Classification:

707776, 707777, 707778, 707726

Abstract:

Systems and methods that integrate user assigned association among a plurality of resources or entities. The subject innovation employs an association component that relates such resources or entities, based on aggregate of user notions that are assigned for relationships; and/or based on how users perceive existence of relationships among such resources. Accordingly, resources can be related (e. g. , linked, matched, tagged and the like) based on relevance of collective user behavior during tagging.

US Patent:

20220207745, Jun 30, 2022

Filed:

Mar 18, 2022

Appl. No.:

17/655493

Inventors:

- San Jose CA, US
Long Mai - Portland OR, US
Jun Hao Liew - Singapore, SG
Brian Price - San Jose CA, US

International Classification:

G06T 7/12
G06T 7/194
G06T 3/40
G06V 10/25

Abstract:

The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.

US Patent:

20200202533, Jun 25, 2020

Filed:

Dec 24, 2018

Appl. No.:

16/231746

Inventors:

- San Jose CA, US
Long Mai - Portland OR, US
Jun Hao Liew - Singapore, SG
Brian Price - San Jose CA, US

International Classification:

G06T 7/12
G06T 7/194
G06K 9/32
G06T 3/40

Abstract:

The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.