P
Paul A. Viola
Researcher at Microsoft
Publications - 115
Citations - 62579
Paul A. Viola is an academic researcher from Microsoft. The author has contributed to research in topics: Parsing & Boosting (machine learning). The author has an hindex of 52, co-authored 115 publications receiving 59853 citations. Previous affiliations of Paul A. Viola include IBM & Wilmington University.
Papers
More filters
Patent
Parsing of ink annotations
TL;DR: Annotation recognition and parsing is accomplished by first recognizing and grouping shapes such that relationships between the annotations and the underlying text and/or images can be determined as discussed by the authors, followed by categorization of recognized annotations according to predefined types.
Patent
Ranking search results using feature score distributions
TL;DR: In this paper, a distribution of document features, feature value coefficients, and/or document ranking values can be generated based on sampled values from the distribution of values, which can allow the relative ranking of a document to vary.
Patent
Feature selection and extraction
Gang Hua,Paul A. Viola,David Liu +2 more
TL;DR: In this article, the first-order image features are selected for image classification from an image feature pool, initially populated with pre-extracted first order image features, which are paired with previously selected firstorder classifying features to generate higher-order features.
Patent
Application of grammatical parsing to visual recognition tasks
Paul A. Viola,Michael Shilman +1 more
TL;DR: In this article, image recognition is utilized to facilitate in scoring parse trees for two-dimensional recognition tasks, where trees and subtrees are rendered as images and then utilized to determine parsing scores.
Patent
Face recognition using discriminatively trained orthogonal tensor projections
TL;DR: In this paper, a discriminatively trained orthogonal rank one tensor projections are used for face recognition, which minimizes intraclass differences between instances of the same face while maximizing interclass differences between the face and faces of different people.