Search

Jingming Dong

from Bellevue, WA
Age ~35
Get Report
Related to:
Dong YilanJunzi Dong, 35
Connected to:
Aaron P Dong, 33Alfred Y Dong, 41Amy N Dong, 53Austin N Dong, 31Bill Y Dong, 62Bruce Y Dong, 92Carolyn Dong, 33Charlie T Dong, 65Chenchen Dong, 41Christopher D Dong, 49

Jingming Dong Phones & Addresses

  • Bellevue, WA
  • 4008A Linden Ave N, Seattle, WA 98103
  • Los Angeles, CA

Work

Company: Facebook Jun 2017 to Aug 2018 Position: Staff research scientist

Education

Degree: Doctorates, Doctor of Philosophy School / High School: University of California, Los Angeles 2011 to 2017 Specialities: Computer Science, Philosophy

Skills

Machine Learning • C++ • Computer Vision • Algorithms • Matlab • Deep Learning • Python • Pattern Recognition

Industries

Computer Software

Resumes

Resumes

Jingming Dong Photo 1

Research Scientist

View page
Location:
4008a Linden Ave north, Seattle, WA 98103
Industry:
Computer Software
Work:
Facebook Jun 2017 - Aug 2018
Staff Research Scientist
Ucla Sep 2011 - Jun 2017
Graduate Student Researcher
Nvidia Jun 2015 - Sep 2015
Research Scientist Intern
Microsoft Feb 2010 - Apr 2010
Program Manager Intern
Oculus Vr Feb 2010 - Apr 2010
Research Scientist
Education:
University of California, Los Angeles 2011 - 2017
Doctorates, Doctor of Philosophy, Computer Science, Philosophy Fudan University 2007 - 2011
Bachelors, Bachelor of Science, Computer Science
Skills:
Machine Learning
C++
Computer Vision
Algorithms
Matlab
Deep Learning
Python
Pattern Recognition

Publications

Us Patents

Dsp-Sift: Domain-Size Pooling For Image Descriptors For Image Matching And Other Applications

View page
US Patent:
20170243084, Aug 24, 2017
Filed:
Nov 7, 2016
Appl. No.:
15/345373
Inventors:
- Oakland CA, US
Jingming Dong - Los Angeles CA, US
Assignee:
THE REGENTS OF THE UNIVERSITY OF CALIFORNIA - Oakland CA
International Classification:
G06K 9/62
G06K 9/46
G06K 9/52
Abstract:
A variation of scale-invariant feature transform (SIFT) based on pooling gradient orientations across different domain sizes, in addition to spatial locations. The resulting descriptor is called DSP-SIFT, and it outperforms other methods in wide-baseline matching benchmarks, including those based on convolutional neural networks, despite having the same dimension of SIFT and requiring no training. Problems of local representation of imaging data are also addressed as computation of minimal sufficient statistics that are invariant to nuisance variability induced by viewpoint and illumination. A sampling-based and a point-estimate based approximation of such representations are described.
Control profile
Jingming Dong from Bellevue, WA, age ~35 Get Report