Search

Ross B Girshick

from Seattle, WA
Age ~42
Get Report
Related to:
David Brook Girshick, 74Rachel L Girshick, 45Barbara A Girshick, 73
Connected to:
Jeffrey Girshman, 51Todd H Girshon, 55Tom M Girskis, 61Ryan M Girst, 50Della E Girt, 97Stacey D Girt, 63Betty D Girten, 79Carrie L Girten, 36Jeffrey T Girten, 37Nicole C Girtman, 51

Ross Girshick Phones & Addresses

  • 1815 N 37Th St, Seattle, WA 98103
  • Berkeley, CA
  • Chicago, IL
  • Cambridge, MA
  • Spokane, WA
  • Waltham, MA
  • Allston, MA

Work

Company: Uc berkeley Sep 2012 Position: Post-doctoral fellow

Skills

Latex • Algorithms • Python • Matlab • C++ • Computer Science • Pattern Recognition • Image Processing • Artificial Intelligence • Machine Learning

Industries

Research

Resumes

Resumes

Ross Girshick Photo 1

Post-Doctoral Fellow

View page
Location:
1815 north 37Th St, Seattle, WA 98103
Industry:
Research
Work:
Uc Berkeley
Post-Doctoral Fellow
Skills:
Latex
Algorithms
Python
Matlab
C++
Computer Science
Pattern Recognition
Image Processing
Artificial Intelligence
Machine Learning

Publications

Us Patents

Human Body Pose Estimation

View page
US Patent:
8638985, Jan 28, 2014
Filed:
Mar 3, 2011
Appl. No.:
13/040205
Inventors:
Jamie Daniel Joseph Shotton - Cambridge, GB
Shahram Izadi - Cambridge, GB
Otmar Hilliges - Cambridge, GB
David Kim - Cambridge, GB
David Geoffrey Molyneaux - Oldham, GB
Matthew Darius Cook - Cambridge, GB
Pushmeet Kohli - Cambridge, GB
Antonio Criminisi - Hardwick, GB
Ross Brook Girshick - Chicago IL, US
Andrew William Fitzgibbon - Cambridge, GB
Assignee:
Microsoft Corporation - Redmond WA
International Classification:
G06K 9/00
US Classification:
382103, 382181
Abstract:
Techniques for human body pose estimation are disclosed herein. Images such as depth images, silhouette images, or volumetric images may be generated and pixels or voxels of the images may be identified. The techniques may process the pixels or voxels to determine a probability that each pixel or voxel is associated with a segment of a body captured in the image or to determine a three-dimensional representation for each pixel or voxel that is associated with a location on a canonical body. These probabilities or three-dimensional representations may then be utilized along with the images to construct a posed model of the body captured in the image.

Predicting Joint Positions

View page
US Patent:
20120239174, Sep 20, 2012
Filed:
Mar 17, 2011
Appl. No.:
13/050858
Inventors:
Jamie Daniel Joseph Shotton - Cambridge, GB
Pushmeet Kohli - Cambridge, GB
Ross Brook Girshick - Chicago IL, US
Andrew Fitzgibbon - Cambridge, GB
Antonio Criminisi - Cambridge, GB
Assignee:
Microsoft Corporation - Redmond WA
International Classification:
G06F 19/00
G06K 9/62
G06K 9/68
US Classification:
700 93, 382218, 382159
Abstract:
Predicting joint positions is described, for example, to find joint positions of humans or animals (or parts thereof) in an image to control a computer game or for other applications. In an embodiment image elements of a depth image make joint position votes so that for example, an image element depicting part of a torso may vote for a position of a neck joint, a left knee joint and a right knee joint. A random decision forest may be trained to enable image elements to vote for the positions of one or more joints and the training process may use training images of bodies with specified joint positions. In an example a joint position vote is expressed as a vector representing a distance and a direction of a joint position from an image element making the vote. The random decision forest may be trained using a mixture of objectives.

Systems And Methods For Optimizing Pose Estimation

View page
US Patent:
20190171871, Jun 6, 2019
Filed:
Dec 31, 2018
Appl. No.:
16/236974
Inventors:
- Menlo Park CA, US
Peter Vajda - Palo Alto CA, US
Kevin Matzen - Seattle WA, US
Ross Girshick - Seattle WA, US
International Classification:
G06K 9/00
G06N 7/00
G06N 20/00
G06F 17/18
G06T 7/73
Abstract:
In one embodiment, a system may access first, second, and third probability models that are respectively associated with predetermined first and second body parts and a predetermined segment connecting the first and second body parts. Each model includes probability values associated with regions in an image, with each value representing the probability of the associated region containing the associated body part or segment. The system may select a first and second region based on the first probability model and a third region based on the second probability model. Based on the third probability model, the system may compute a first probability score for regions connecting the first and third regions and a second probability score for regions connecting the second and third regions. Based on the first and second probability scores, the system may select the first region to indicate where the predetermined first body part appears in the image.

Machine-Learning Models Based On Non-Local Neural Networks

View page
US Patent:
20190156210, May 23, 2019
Filed:
Nov 15, 2018
Appl. No.:
16/192649
Inventors:
- Menlo Park CA, US
Ross Girshick - Seattle WA, US
Xiaolong Wang - Pittsburgh PA, US
International Classification:
G06N 3/08
G06N 3/04
G06F 17/15
G06F 17/30
Abstract:
In one embodiment, a method includes training a baseline machine-learning model based on a neural network comprising a plurality of stages, wherein each stage comprises a plurality of neural blocks, accessing a plurality of training samples comprising a plurality of content objects, respectively, determining one or more non-local operations, wherein each non-local operation is based on one or more pairwise functions and one or more unary functions, generating one or more non-local blocks based on the plurality of training samples and the one or more non-local operations, determining a stage from the plurality of stages of the neural network, and training a non-local machine-learning model by inserting each of the one or more non-local blocks in between at least two of the plurality of neural blocks in the determined stage of the neural network.

Object Detection And Classification In Images

View page
US Patent:
20170206431, Jul 20, 2017
Filed:
Jan 20, 2016
Appl. No.:
15/001417
Inventors:
- Redmond WA, US
Ross Girshick - Seattle WA, US
Shaoqing Ren - Beijing, CN
Kaiming He - Beijing, CN
International Classification:
G06K 9/46
G06N 3/08
G06F 17/30
G06K 9/62
Abstract:
Systems, methods, and computer-readable media for providing fast and accurate object detection and classification in images are described herein. In some examples, a computing device can receive an input image. The computing device can process the image, and generate a convolutional feature map. In some configurations, the convolutional feature map can be processed through a Region Proposal Network (RPN) to generate proposals for candidate objects in the image. In various examples, the computing device can process the convolutional feature map with the proposals through a Fast Region-Based Convolutional Neural Network (FRCN) proposal classifier to determine a class of each object in the image and a confidence score associated therewith. The computing device can then provide a requestor with an output including the object classification and/or confidence score.
Control profile
Ross B Girshick from Seattle, WA, age ~42 Get Report