Browsing by Author "Kıraç, Mustafa Furkan"
Now showing items 1-20 of 25
-
Adapting bilateral networks to monocular depth estimation for real-time inference
Monocular Depth Estimation (MDE) is a fundamental computer vision application area for many industry-related advances. Due to its deployment needs, the inference time of the depth estimation algorithm also plays a crucial ... -
ADVISOR: An adjustable framework for test oracle automation of visual output systems
Genç, A. E.; Sözer, Hasan; Kıraç, Mustafa Furkan; Aktemur, Tankut Barış (IEEE, 2020-09)Test oracles differentiate between the correct and incorrect system behavior. Automation of test oracles for visual output systems mainly involves image comparison, where a snapshot of the output is compared with respect ... -
Alt kesit seviyeleri arasında oy çoğunluğu ile sahne tanıma
In this paper, scene recognition problem, which is a frequently-studied field of computer vision, is tackled. Proposed algorithm utilizes bag of words (BoW) method along with considering sub-segments in the image during ... -
Automated maintenance support for data-tier software
Data-tier software includes the data model and business logic of enterprise systems, and it is subject to long-term maintenance. Even though the user interface of these systems can be completely replaced, data-tier software ... -
Automatically learning usage behavior and generating event sequences for black-box testing of reactive systems
Kıraç, Mustafa Furkan; Aktemur, Tankut Barış; Sözer, Hasan; Gebizli, C. Ş. (The ACM Digital Library, 2019-06)We propose a novel technique based on recurrent artificial neural networks to generate test cases for black-box testing of reactive systems. We combine functional testing inputs that are automatically generated from a model ... -
Autotuning runtime specialization for sparse matrix-vector multiplication
Yılmaz, Buse; Aktemur, Tankut Barış; Garzaran, M. J.; Kamin, S.; Kıraç, Mustafa Furkan (ACM, 2016-04)Runtime specialization is used for optimizing programs based on partial information available only at runtime. In this paper we apply autotuning on runtime specialization of Sparse Matrix-Vector Multiplication to predict ... -
Clothing image retrieval with triplet capsule networks
Kınlı, Osman Furkan (2019-08-19)Clothing image retrieval has become more important after some major developments in Computer Science and the emergence of e-commerce. Recent studies generally attack this problem by using Convolutional Neural Networks ... -
Description-aware fashion image inpainting with convolutional neural networks in coarse-to-fine manner
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (The ACM Digital Library, 2020-04-14)Inpainting a particular missing region in an image is a challenging vision task, and promising improvements on this task have been achieved with the help of the recent developments in vision-related deep learning studies. ... -
An ecologically valid reference frame for perspective invariant action recognition
In robotics, objects and body parts can be represented in various coordinate frames to ease computation. In biological systems, body or body part centered coordinate frames have been proposed as possible reference frames ... -
Fashion image retrieval with capsule networks
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (IEEE, 2019)In this study, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based design of Capsule Network architecture with two ... -
Hierarchically constrained 3D hand pose estimation using regression forests from single frame depth data
Kıraç, Mustafa Furkan; Kara, Y. E.; Akarun, L. (Elsevier, 2014-12-01)The emergence of inexpensive 2.5D depth cameras has enabled the extraction of the articulated human body pose. However, human hand skeleton extraction still stays as a challenging problem since the hand contains as many ... -
Image denoising using deep convolutional autoencoder with feature pyramids
Çetinkaya, Ekrem; Kıraç, Mustafa Furkan (TÜBİTAK, 2020)Image denoising is 1 of the fundamental problems in the image processing field since it is the preliminary step for many computer vision applications. Various approaches have been used for image denoising throughout the ... -
Image denoising using deep convolutional autoencoders
Çetinkaya, Ekrem (2019-08-19)Image denoising is one of the fundamental problems in image processing eld since it is required by many computer vision applications. Various approaches have been used in image denoising throughout the years from spatial ... -
Increasing visual detail for tv watchers with color vision deficiencies by using image processing methods
Kırgız, Gamze (2018-05)There are three types of cone cells in the human retina that respond to different color spectrums. The signals generated by these cone cells are combined and the color information is interpreted. Color blindness, or color ... -
Instagram filter removal on fashionable images
Kınlı, Osman Furkan; Özcan, Barış; Kıraç, Mustafa Furkan (IEEE, 2021-06)Social media images are generally transformed by filtering to obtain aesthetically more pleasing appearances. However, CNNs generally fail to interpret both the image and its filtered version as the same in the visual ... -
Introduction of a spatio-temporal mapping based POE method for outdoor spaces: Suburban university campus as a case study
Göçer, Özgür; Göçer, K.; Başol, Altuğ Melik; Kıraç, Mustafa Furkan; Özbil, A.; Bakovic, M.; Siddiqui, Faizan Pervez; Özcan, Barış (Elsevier, 2018-11)Outdoor spaces are important to sustainable cities because they establish a common identity for social life by improving quality of urban living. The relation between outdoor spaces and building groups, competency, use ... -
Multi-scale binary similarity a local binary pattern variant for face recognition
Tavlı, Ahmet (2018-08)Face recognition problem were studied for more than four-decade, and many descriptors and neural network architectures have been proposed since then. The aim is simple, extract features from the same subjects for training ... -
Negotiation-based decentralized conflict resolution in multi-agent path finding
This thesis addresses the problem of Multi-Agent Path Finding problem where multiple agents aim to reach their destination in a grid world without any colli sion. It aims to provide a solution achieving good trade-off ... -
Pedestrian tracking in outdoor spaces of a suburban university campus for the investigation of occupancy patterns
Göçer, Özgür; Göçer, K.; Özcan, Barış; Bakovic, M.; Kıraç, Mustafa Furkan (Elsevier, 2019-02)The design of a livable and comfortable environment has been one of the main aims of sustainable university campus design. The creation of outdoor spaces for accommodating amenities has a positive effect on users with ... -
Performance evaluation of unfolded sparse matrix-vector multiplication
Akgün, İbrahim Ümit (2015-01)Sparse matrix-vector multiplication (spMV) is a kernel operation in scientific com- putation. There exist problems where a matrix is repeatedly multiplied by many different vectors. For such problems, specializing the spMV ...
Share this page
