V
Vincent Oria
Researcher at New Jersey Institute of Technology
Publications - 100
Citations - 2301
Vincent Oria is an academic researcher from New Jersey Institute of Technology. The author has contributed to research in topics: Query optimization & Image retrieval. The author has an hindex of 17, co-authored 98 publications receiving 2092 citations. Previous affiliations of Vincent Oria include University of Alberta.
Papers
More filters
MINDEX: An efficient index structure for salient-object-based queries in video databases
TL;DR: This paper proposes a multilevel index structure (MINDEX) to efficiently handle the salient-object-based queries with different levels of constraints and presents experimental results showing the performance of different methods of MINDEX construction.
Book ChapterDOI
Flexible Aggregate Similarity Search in High-Dimensional Data Sets
TL;DR: In this paper, the authors proposed two approximation algorithms, one for the sum and avg variants of FANN, and the other for the max variant, for query results with good accuracy, while at the same time being very efficient.
Posted Content
Prediction of Solar Proton Events with Machine Learning: Comparison with Operational Forecasts and "All-Clear" Perspectives
Viacheslav Sadykov,Alexander G. Kosovichev,Irina N. Kitiashvili,Vincent Oria,Gelu M. Nita,Egor Illarionov,Patrick O'Keefe,Yucheng Jiang,Sheldon Fereira,Aatiya Ali +9 more
TL;DR: In this article, the authors considered the problem of daily prediction of solar Proton Events (SPEs) based on the characteristics of the magnetic fields in solar active regions (ARs), preceding soft X-ray and proton fluxes, and statistics of solar radio bursts.
Proceedings Article
Using multi-scale histograms to answer pattern existence and shape match queries over time series data
Proceedings ArticleDOI
Recommender system for MIR research community
TL;DR: This demonstration shows a recommender system for the Music Information Retrieval (MIR) research community that extracts the key topics and tags by analyzing the ten-year cumulative ISMIR proceedings, and recommends papers and research colleagues to users in an interactive way.