The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 09, 2017

Filed:

Apr. 16, 2014
Applicant:

The Penn State Research Foundation, University Park, PA (US);

Inventors:

James Z. Wang, State College, PA (US);

Neela Sawant, Seattle, WA (US);

Jia Li, State College, PA (US);

Assignee:

The Penn State Research Foundation, University Park, PA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06K 9/62 (2006.01);
U.S. Cl.
CPC ...
G06K 9/6256 (2013.01); G06K 9/62 (2013.01);
Abstract

Automatic selection of training images is enhanced using an instance-weighted mixture modeling framework called ARTEMIS. An optimization algorithm is derived that in addition to mixture parameter estimation learns instance-weights, essentially adapting to the noise associated with each example. The mechanism of hypothetical local mapping is evoked so that data in diverse mathematical forms or modalities can be cohesively treated as the system maintains tractability in optimization. Training examples are selected from top-ranked images of a likelihood-based image ranking. Experiments indicate that ARTEMIS exhibits higher resilience to noise than several baselines for large training data collection. The performance of ARTEMIS-trained image annotation system is comparable to using manually curated datasets.


Find Patent Forward Citations

Loading…