Şifa Gül Demiryürek | Generative Models for Computer Vision | Outstanding Scientist Award

Published on by Computer Vision Awards

Dr. Şifa Gül Demiryürek | Generative Models for Computer Vision | Outstanding Scientist Award

Lecturer | Aksaray University | Turkey

Dr. Şifa Gül Demiryürek is a researcher specializing in acoustics, dynamics, vibration control, nonlinear structures, and metamaterials, with a growing body of work that bridges fundamental mechanics and applied engineering. Her research focuses on low-frequency broadband vibration damping, nonlinear passive particle dampers, and metamaterial-inspired structures aimed at improving stability, efficiency, and durability in modern mechanical systems.She has authored 11 scientific documents, accumulating 19 citations with an h-index of 3, reflecting the emerging impact of her contributions. Her early work includes the experimental study of thermal-mixing phenomena in coaxial jets published in the Journal of Thermophysics and Heat Transfer demonstrating her multidisciplinary foundation in fluid–thermal interactions. Transitioning toward structural dynamics  her doctoral research at the University of Sheffield advanced the understanding of periodically arranged nonlinear particle dampers under low-amplitude excitation providing new insights into damping mechanisms critical for lightweight and high-performance structures.Dr. Demiryürek has collaborated with notable researchers such as A. Krynkin and J. Rongong contributing to recognized venues including DAGA, ACOUSTICS Proceedings, and the Institute of Acoustics. Her studies on metamaterial-based dampers and locally resonating structures highlight innovative strategies for vibration mitigation particularly in the low-frequency regime where traditional dampers are less effective. Her works further expand this direction with investigations on dynamic behavior of thermoplastics and material resonance considerations for wind turbine towers addressing contemporary engineering challenges related to sustainability and structural reliability.In addition to research publications she has contributed educational materials including Introduction to Metamaterials  supporting broader knowledge dissemination in emerging engineering domains. Her collaborations in applied mechanics such as the numerical evaluation of electric motorcycle chassis demonstrate a commitment to integrating theoretical advances into practical real-world applications.Through her focused work at the intersection of vibration engineering and metamaterial science Şifa Gül Demiryürek is contributing to next-generation solutions for safer quieter and more efficient mechanical systems with potential societal impact across manufacturing transportation renewable energy and advanced materials engineering.

Profiles: Googlescholar | Scopus | ORCID

Featured Publications

1.Demiryürek, S. G., Kok, B., Varol, Y., Ayhan, H., & Oztop, H. F. (2018). Experimental investigation of thermal-mixing phenomena of a coaxial jet with cylindrical obstacles. Journal of Thermophysics and Heat Transfer, 32(2), 273–283. Cited By: 5

2. Demiryürek, S. G. (2022). Periodically arranged nonlinear passive particle dampers under low-amplitude excitation (Doctoral research, University of Sheffield). Cited By: 3

3. Demiryürek, S. G., & Krynkin, A. (2021). Low-frequency broadband vibration damping using the nonlinear damper with metamaterial properties. In DAGA 2021 Conference Proceedings (pp. 94–96). Cited By: 3

4.Demiryürek, S. G., Krynkin, A., & Rongong, J. (2020). Modelling of nonlinear dampers under low-amplitude vibration. In ACOUSTICS 2020 Proceedings. Cited By: 3

5.Demiryürek, S. G., Krynkin, A., & Rongong, J. (2019). Non-linear metamaterial structures: Array of particle dampers. Universitätsbibliothek der RWTH Aachen. Cited By: 3

Dr. Şifa Gül Demiryürek’s research advances next-generation vibration damping and metamaterial technologies, enabling safer, quieter, and more efficient mechanical systems across industries. Her contributions support innovation in sustainable engineering from wind energy structures to lightweight transportation strengthening global efforts toward resilient, high-performance designs.

Generative Models for Computer Vision

Published on by Computer Vision Awards

Introduction of Generative Models for Computer Vision

Generative Models for Computer Vision represent a cutting-edge research area that combines computer vision with generative modeling techniques, particularly deep learning, to create artificial systems capable of generating realistic visual content. These models have revolutionized various applications, including image synthesis, style transfer, data augmentation, and even content creation in the realms of art and entertainment.

Subtopics in Generative Models for Computer Vision:

  1. Generative Adversarial Networks (GANs): GANs are a foundational technology in generative modeling. Researchers explore novel architectures, training strategies, and applications of GANs for image generation, super-resolution, and style transfer.
  2. Variational Autoencoders (VAEs): VAEs are used for probabilistic generative modeling and have applications in image reconstruction, anomaly detection, and data generation with uncertainty estimation.
  3. Conditional Generation: Techniques for conditioning generative models on specific attributes or information, such as generating images of particular objects or scenes based on textual descriptions or desired characteristics.
  4. Style Transfer and Domain Adaptation: Research focuses on transferring artistic styles, domain adaptation, and image-to-image translation using generative models. This enables transformations like turning day scenes into night or changing artistic styles.
  5. Image-to-Image Translation: Generative models are used for tasks such as converting sketches to photographs, enhancing image quality, or transforming images to follow specific artistic styles.

Generative Models for Computer Vision research continues to advance the capabilities of machines to generate, transform, and understand visual content, with applications ranging from creative art generation to practical image enhancement and manipulation. These subtopics highlight the diverse and impactful avenues of exploration within this field.

[post_grid id="19552"]