E
Eric Nowak
Researcher at French Institute for Research in Computer Science and Automation
Publications - 8
Citations - 1776
Eric Nowak is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Contextual image classification & Similarity measure. The author has an hindex of 5, co-authored 8 publications receiving 1740 citations.
Papers
More filters
Book ChapterDOI
Sampling strategies for bag-of-features image classification
TL;DR: In this article, the authors show experimentally that for a representative selection of commonly used test databases and for moderate to large numbers of samples, random sampling gives equal or better classifiers than the sophisticated multiscale interest operators that are in common use.
Journal ArticleDOI
Randomized Clustering Forests for Image Classification
TL;DR: This work introduces Extremely Randomized Clustering Forests-ensembles of randomly created clustering trees-and shows that they provide more accurate results, much faster training and testing, and good resistance to background clutter.
Proceedings ArticleDOI
Learning Visual Similarity Measures for Comparing Never Seen Objects
Eric Nowak,Frédéric Jurie +1 more
TL;DR: An algorithm that learns a similarity measure for comparing never seen objects that is fast to learn, robust due to the redundant information they carry and they have been proved to be very good clusterers is proposed.
Journal Article
Sampling Strategies for Bag-of-Features Image Classification
TL;DR: It is shown experimentally that for a representative selection of commonly used test databases and for moderate to large numbers of samples, random sampling gives equal or better classifiers than the sophisticated multiscale interest operators that are in common use.
Proceedings ArticleDOI
Vehicle Categorization: Parts for Speed and Accuracy
Eric Nowak,Frédéric Jurie +1 more
TL;DR: A high-level data transformation algorithm and a feature selection scheme adapted to hierarchical SVM classifiers to improve the performance of part-based vehicle models to address the trade-off between the number of parts included in the vehicle models and the recognition rate.