The detailed information of my presentations to be held within the scope of BLU 596E is as follows:
No 1
Student ID Number 708191019
Name Surname Muhammet Bolat
Tittle Super Resolution with Deep Learning(Derin Öğrenme ile Süper Çözünürlük)
Abstract Image super-resolution (SR) aims to reconstruct a high-resolution image from a single low-resolution image. Aim of the presentation is to mention how to implement deep learning techniques for this problem and available state-of-art methods. Finally, we are going to discuss the results.süper çözünürlük yöntemleriyle birleştirilmesini ve alınan sonuçları sunmayı planlamaktayım.
Advisors' Name Surname Lütfiye Durak Ata, Nurullah Çalık(Eş Danışman)
Date 30.11.2021
Hour 9:30

No 2
Student ID Number 708201004
Name Surname Mehmet Mert Tuncer
Tittle Physical Layer Security
Abstract Physical layer security originated from the pioneering work of Shannon, who laid the foundation for secrecy systems and then, the well-known wiretap channel was introduced by Wyner in 1975.
Specifically, to define secrecy in terms of the ability to transmit a secret information, in this work Wyner provided a guarantee that the eavesdropping channel was a degraded, but much more noisy form of the legitimate connection, allowing the secrecy capacity to be the highest rate of data transmission that could be transmitted securely while avoiding the risk of being decrypted by an eavesdropper. Because of the wireless medium’s overt character, the transmitted signal will be received by legitimate and illegitimate receivers alike. The transmitted information may be potentially exposed to various security attacks, thus providing security in wireless networks is a major issue that must be investigated on a massive scale the wireless network
Advisors' Name Surname Lütfiye Durak Ata
Date 7.12.2021
Hour 9:30

No 3
Student ID Number 704202002
Name Surname Esra Ergun
Tittle Joint Detection and Identification Feature Learning for Person Search
Abstract Existing Re-Identification networks focus on retrieving manually cropped query images from manually cropped gallery images. Real-world applications include finding criminals, cross-camera target tracking, person activity analysis, etc. Processing with manually cropped images is not a fit for real-world applications. Person search focuses on retrieving a
query image from whole gallery images. This study handles pedestrian detection and person search jointly in a single convolutional neural network. In the original work, an Online Instance Matching loss is proposed to train the network effectively. To validate the approach a largescale benchmark dataset is collected (CHUK-SYSU) which contains 18,184 images, 8,432 identities, and 96, 143 pedestrian bounding boxes. The results showed the superiority of
Online Instance Matching Loss over conventional Softmax loss.
Advisors' Name Surname Ertugrul Karacuha
Date 14.12.2021
Hour 9:30