scispace - formally typeset
E

Ezgi Can Ozan

Researcher at Tampere University of Technology

Publications -  15
Citations -  112

Ezgi Can Ozan is an academic researcher from Tampere University of Technology. The author has contributed to research in topics: Nearest neighbor search & Vector quantization. The author has an hindex of 5, co-authored 15 publications receiving 95 citations. Previous affiliations of Ezgi Can Ozan include Middle East Technical University.

Papers
More filters
Proceedings ArticleDOI

Visual saliency by extended quantum cuts

TL;DR: This study proposes an unsupervised, state-of-the-art saliency map generation algorithm which is based on a recently proposed link between quantum mechanics and spectral graph clustering, Quantum Cuts and introduces a novel approach to propose several saliency maps.
Journal ArticleDOI

Competitive Quantization for Approximate Nearest Neighbor Search

TL;DR: An extensive set of experimental results and comparative evaluations show that CompQ outperforms the-state-of-the-art while retaining a comparable computational complexity.
Journal ArticleDOI

K-Subspaces Quantization for Approximate Nearest Neighbor Search

TL;DR: This paper proposes an iterative approach to minimize the quantization error in order to create a novel quantization scheme, which outperforms the state-of-the-art algorithms.
Journal ArticleDOI

Extended quantum cuts for unsupervised salient object extraction

TL;DR: Extended Quantum Cuts is proposed, which consistently achieves an exquisite performance over all benchmark saliency detection datasets, containing around 18 k images in total and outperforms the state-of-the-art on a recently announced RGB-Depth saliency dataset.
Book ChapterDOI

An Optimized k-NN Approach for Classification on Imbalanced Datasets with Missing Data

TL;DR: The proposed solution performs better in terms of the given challenge metric compared to the traditional classification methods such as SVM, AdaBoost or Random Forests.