scispace - formally typeset
Search or ask a question
Institution

Istanbul Technical University

EducationIstanbul, Turkey
About: Istanbul Technical University is a education organization based out in Istanbul, Turkey. It is known for research contribution in the topics: Fuzzy logic & Large Hadron Collider. The organization has 12889 authors who have published 25081 publications receiving 518242 citations. The organization is also known as: İstanbul Teknik Üniversitesi & Technical University of Istanbul.


Papers
More filters
Proceedings ArticleDOI
01 Jan 2016
TL;DR: Analysis of the influence of image degradations on the performance of deep CNN-based face recognition approaches using the standard LFW closed-set identification protocol indicated that blur, noise, and occlusion cause a significant decrease in performance, while deep CNN models are found to be robust to distortions, such as color distortions and change in color balance.
Abstract: Face recognition approaches that are based on deep convolutional neural networks (CNN) have been dominating the field. The performance improvements they have provided in the so called in-the-wild datasets are significant, however, their performance under image quality degradations have not been assessed, yet. This is particularly important, since in real-world face recognition applications, images may contain various kinds of degradations due to motion blur, noise, compression artifacts, color distortions, and occlusion. In this work, we have addressed this problem and analyzed the influence of these image degradations on the performance of deep CNN-based face recognition approaches using the standard LFW closed-set identification protocol. We have evaluated three popular deep CNN models, namely, the AlexNet, VGG-Face, and GoogLeNet. Results have indicated that blur, noise, and occlusion cause a significant decrease in performance, while deep CNN models are found to be robust to distortions, such as color distortions and change in color balance.

123 citations

Journal ArticleDOI
TL;DR: It is found that for sufficient temporal resolution, POD-based methods outperform Kriging interpolation, however, for insufficient temporalresolution, large spatial gappiness or for flow fields with black zones, Kriged interpolation is more effective.

123 citations

Journal ArticleDOI
01 Jul 2011-Lithos
TL;DR: In this article, the authors provide geochronological and geochemical data on a suite of Early Eocene intrusions from northeast Turkey and discuss their origin within a regional tectonic framework.

123 citations

Journal ArticleDOI
TL;DR: In this paper, a macrophotoinitiators containing thioxanthone (TX) moieties as side chains were synthesized by using double click chemistry strategy; combining in-situ 1,3-dipolar azide−alkyne [3 + 2] and thermor...
Abstract: Macrophotoinitiators containing thioxanthone (TX) moieties as side chains were synthesized by using “double click chemistry” strategy; combining in-situ 1,3-dipolar azide−alkyne [3 + 2] and thermor...

123 citations

Journal ArticleDOI
TL;DR: In this paper, a block copolymer (BASFk Pluronic p123) was employed as a template to generate the mesoporous structure and an ultraviolet (UV) illumination method was employed to remove the polymer templates at room temperature.

123 citations


Authors

Showing all 13155 results

NameH-indexPapersCitations
David Miller2032573204840
H. S. Chen1792401178529
Hyun-Chul Kim1764076183227
J. N. Butler1722525175561
Andrea Bocci1722402176461
Bradley Cox1692150156200
Yang Gao1682047146301
J. E. Brau1621949157675
G. A. Cowan1592353172594
David Cameron1541586126067
Andrew D. Hamilton1511334105439
Jongmin Lee1502257134772
A. Artamonov1501858119791
Teresa Lenz1501718114725
Carlos Escobar148118495346
Network Information
Related Institutions (5)
National Technical University of Athens
31.2K papers, 723.5K citations

91% related

Polytechnic University of Catalonia
45.3K papers, 949.3K citations

90% related

Polytechnic University of Turin
41.3K papers, 789.3K citations

90% related

Delft University of Technology
94.4K papers, 2.7M citations

89% related

Royal Institute of Technology
68.4K papers, 1.9M citations

89% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
2023137
2022338
20211,860
20201,772
20191,834
20181,643