Tarkan Aydın

Bahçeşehir University — Turkey

Computer Science · Physical Sciences

7h-index646citations34works1.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Vision and Imaging(12), Advanced Image and Video Retrieval Techniques(7), Image Processing Techniques and Applications(7), Advanced Neural Network Applications(6), Robotics and Sensor-Based Localization(6)

Publications34 total

End-to-end human parsing and detection optimized for resource-constrained devices
Scientific Reports·2025Open Access
Performance Assessment of Functional Upper Extremity Exercises with Deep Learning
Firat University Journal of Experimental and Computational Engineering·2025Open Access
NiNformer: a network in network transformer with token mixing generated gating function
Neural Computing and Applications·2025Open Access
Predicting Heatstroke Risk and Preventing Health Complications
2025· 1 cited
Assistive Visual Tool: Enhancing Safe Navigation with Video Remapping in AR Headsets
Lecture notes in computer science·2025
Edge devices friendly multi-human parsing with lightweight encoding and multi-scale self-attention based decoding
Multimedia Tools and Applications·2024· 4 cited
WNet: A dual‐encoded multi‐human parsing network
IET Image Processing·2024· 5 citedOpen Access
Activator: GLU Activation Function as the Core Component of a Vision Transformer
arXiv (Cornell University)·2024Open Access
NiNformer: A Network in Network Transformer with Token Mixing Generated Gating Function
arXiv (Cornell University)·2024Open Access
Time Multipoint Nonlocal Problem for a Stochastic Schrödinger Equation
Journal of Computational Mathematics·2024Open Access
ARVA: An Augmented Reality-Based Visual Aid for Mobility Enhancement Through Real-Time Video Stream Transformation
IEEE Access·2024· 3 citedOpen Access
Comparatively Studying Modern Optimizers Capability for Fitting Vision Transformers
EAI/Springer Innovations in Communication and Computing·2024
Hybrid CNN+Transformer for Diabetic Retinopathy Recognition and Grading
2023· 7 cited
Stereoscopic video quality measurement with fine-tuning 3D ResNets
Multimedia Tools and Applications·2022· 5 cited
HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)·2022· 10 cited
Performance Assessment of Physiotherapy and Rehabilitation Exercises with Deep Learning
2022 30th Signal Processing and Communications Applications Conference (SIU)·2022· 1 cited
Numerical Approximation for 2-Dimensional Schrödinger Equation Using Modified Gauss Elimination Method
European Journal of Science and Technology·2022Open Access
HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model
arXiv (Cornell University)·2022· 1 citedOpen Access
PDS-Net: A novel point and depth-wise separable convolution for real-time object detection
International Journal of Multimedia Information Retrieval·2022· 13 cited
DeepPyNet: A Deep Feature Pyramid Network for Optical Flow Estimation
2021· 2 cited
page 1 of 2Next →

Frequent Co-authors

Md Baharul Islam(12), Masum Shah Junayed(6), Arezoo Sadeghzadeh(6), Yusuf Sinan Akgül(5), Abdullah Nazhat Abdullah(5), A. Tanju Erdem(4), Md Imran Hosen(4), Erkut Arıcan(3), Hassan Imani(2), Lai-Kuan Wong(2), Ali Özer Ercan(2), Md Nur Uddin(2), İlhan Aytutuldu(2), C. Okan Sakar(1), Görkem Serbes(1), Ayşegül Gündüz(1), Hünkar Can Tunç(1), Hatice Nizam Ozogur(1), Betül Erdoğdu Şakar(1), Melih Tütüncü(1)