I
Ilkay Ulusoy
Researcher at Middle East Technical University
Publications - 104
Citations - 2019
Ilkay Ulusoy is an academic researcher from Middle East Technical University. The author has contributed to research in topics: Feature extraction & Object detection. The author has an hindex of 15, co-authored 98 publications receiving 1706 citations.
Papers
More filters
BookDOI
Structural, syntactic, and statistical pattern recognition
TL;DR: A Game-Theoretic Approach to the Enforcement of Global Consistency in Multi-view Feature Matching and an Algorithm for Recovering Camouflage Errors on Moving People are discussed.
Book ChapterDOI
The 2005 PASCAL visual object classes challenge
Mark Everingham,Andrew Zisserman,Christopher Williams,Luc Van Gool,Moray Allan,Christopher M. Bishop,Olivier Chapelle,Navneet Dalal,Thomas Deselaers,Gyuri Dorkó,Stefan Duffner,J Eichhorn,Jason Farquhar,Mario Fritz,Christophe Garcia,Tom Griffiths,Frédéric Jurie,Daniel Keysers,Markus Koskela,Jorma Laaksonen,Diane Larlus,Bastian Leibe,Hongying Meng,Hermann Ney,Bernt Schiele,Cordelia Schmid,Edgar Seemann,John Shawe-Taylor,Amos Storkey,Sandor Szedmak,Bill Triggs,Ilkay Ulusoy,Ville Viitaniemi,Jianguo Zhang +33 more
TL;DR: The PASCAL Visual Object Classes Challenge (PASCALVOC) as mentioned in this paper was held from February to March 2005 to recognize objects from a number of visual object classes in realistic scenes (i.e. not pre-segmented objects).
Journal ArticleDOI
Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey
Görkem Algan,Ilkay Ulusoy +1 more
TL;DR: This paper aims to present algorithms to develop counter algorithms to fade away its negative effects to train deep neural networks efficiently and divides them into one of the two subgroups: noise model based and noise model free methods.
Proceedings ArticleDOI
Generative versus discriminative methods for object recognition
TL;DR: The results support the assertion that neither generative or discriminative approach alone will be sufficient for large scale object recognition, and the techniques for combining them are discussed.
Journal ArticleDOI
Railway Fastener Inspection by Real-Time Machine Vision
TL;DR: An extensive analysis of various methods based on pixel-wise and histogram similarities are conducted and a fusing stage is introduced which combines least correlated approaches also considering the performance upgrade after fusing.