C
Christine D. Piatko
Researcher at Johns Hopkins University
Publications - 72
Citations - 9390
Christine D. Piatko is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Machine translation & Lexicon. The author has an hindex of 28, co-authored 69 publications receiving 8629 citations. Previous affiliations of Christine D. Piatko include Johns Hopkins University Applied Physics Laboratory & National Institute of Standards and Technology.
Papers
More filters
Journal ArticleDOI
An efficient k-means clustering algorithm: analysis and implementation
Tapas Kanungo,David M. Mount,Nathan S. Netanyahu,Christine D. Piatko,Ruth Silverman,Angela Y. Wu +5 more
TL;DR: This work presents a simple and efficient implementation of Lloyd's k-means clustering algorithm, which it calls the filtering algorithm, and establishes the practical efficiency of the algorithm's running time.
Journal ArticleDOI
A visibility matching tone reproduction operator for high dynamic range scenes
TL;DR: A tone reproduction operator is presented that preserves visibility in high dynamic range scenes and introduces a new histogram adjustment technique, based on the population of local adaptation luminances in a scene, that incorporates models for human contrast sensitivity, glare, spatial acuity, and color sensitivity.
Proceedings ArticleDOI
A local search approximation algorithm for k-means clustering
Tapas Kanungo,David M. Mount,Nathan S. Netanyahu,Christine D. Piatko,Ruth Silverman,Angela Y. Wu +5 more
TL;DR: This work considers the question of whether there exists a simple and practical approximation algorithm for k-means clustering, and presents a local improvement heuristic based on swapping centers in and out that yields a (9+ε)-approximation algorithm.
Proceedings ArticleDOI
A visibility matching tone reproduction operator for high dynamic range scenes
TL;DR: A tone reproduction operator is presented that preserves visibility in high dynamic range scenes and introduces a new histogram adjustment technique, based on the population of local adaptation luminances in a scene, that incorporates models for human contrast sensitivity, glare, spatial acuity and color sensitivity.
Proceedings Article
Using ``Annotator Rationales'' to Improve Machine Learning for Text Categorization
TL;DR: It is hypothesize that in some situations, providing rationales is a more fruitful use of an annotator's time than annotating more examples, and presents a learning method that exploits the rationales during training to boost performance significantly on a sample task, namely sentiment classification of movie reviews.