Search

Devi Parikh

from Blacksburg, VA
Get Report
Also known as:
Devi Niru Parikh
Connected to:
Abhi Parikh, 53Alpaben A Parikh, 56Amanda J Parikh, 39Anurag A Parikh, 48Arju B Parikh, 50Arulata A Parikh, 57Aruna A Parikh, 84Atil C Parikh, 47Chinmai Parikh, 32Daksheshkumar R Parikh, 59

Devi Parikh Phones & Addresses

  • Blacksburg, VA
  • 305 Yale Rd, Glassboro, NJ 08028 (856) 863-9098
  • 515 Mullica Hill Rd, Glassboro, NJ 08028 (856) 863-9098
  • Chicago, IL
  • 305 Yale Rd N, Glassboro, NJ 08028 (856) 693-1267

Work

Position: Executive, Administrative, and Managerial Occupations

Education

Degree: High school graduate or higher

Emails

d***[email protected]

Resumes

Resumes

Devi Parikh Photo 1

Research Scientist

View page
Location:
1010 Noel Dr, Menlo Park, CA 94025
Industry:
Research
Work:
Toyota Technological Institute at Chicago (TTIC) since Aug 2009
Research Assistant Professor
Education:
Carnegie Mellon University 2005 - 2009
Ph.D.
Skills:
Machine Learning
Image Processing
Computer Vision
Artificial Intelligence
Pattern Recognition
Signal Processing
Algorithms
Matlab
Computer Science
Mathematical Modeling
Robotics
Programming
Languages:
English
Devi Parikh Photo 2

Devi Parikh

View page

Publications

Us Patents

Efficiently Identifying Images, Videos, Songs Or Documents Most Relevant To The User Based On Attribute Feedback

View page
US Patent:
20140188863, Jul 3, 2014
Filed:
Aug 13, 2013
Appl. No.:
13/965594
Inventors:
- Austin TX, US
Devi Parikh - Blacksburg VA, US
Assignee:
Board of Regents, The University of Texas System - Austin TX
International Classification:
G06F 17/30
US Classification:
707728, 707722
Abstract:
A method, system and computer program product for efficiently identifying images, videos, audio files or documents relevant to a user. Using either manual annotations or learned functions, the method predicts the relative strength of an attribute in an image, video, audio file or document from a pool of images, videos, audio files or documents. At query time, the system presents an initial set of reference images, videos, audio files or documents, and the user selects among them to provide relative attribute feedback. Using the resulting constraints in the multi-dimensional attribute space, the relevance function for the pool of images, videos, audio files or documents is updated and the relevance of the pool of images, videos, audio files or documents is re-computed. This procedure iterates using the accumulated constraints until the top-ranked images, videos, audio files or documents are acceptably close to the user's envisioned image, video, audio file or document.
Control profile
Devi Parikh from Blacksburg, VA Get Report