Yağız Nalçakan, PhD

I am a Postdoctoral Fellow at the Seamless Trans-X Lab (STL), Yonsei University, working on multispectral imaging and robust visual perception for autonomous vehicles. My research lies at the intersection of computer vision, sensor fusion, and intelligent mobility systems.

I received my Ph.D. in Computer Science from the Izmir Institute of Technology, where my dissertation focused on vehicle maneuver detection for advanced driver assistance systems (ADAS) under the supervision of Prof. Dr. Yalin Bastanlar. My doctoral research focused on vehicle maneuver detection for advanced driver assistance systems (ADAS). During my doctoral studies, I also spent a term as a visiting researcher at Seoul National University’s Vehicle Dynamics and Control Laboratory (VDCL) & the Future Mobility Technology Center (FMTC) supported by a research scholarship from TUBITAK (The Scientific and Technological Research Council of Turkey).

My research interests revolve around computer vision and deep learning, with a specialization in multispectral camera systems, perception in adverse weather scenarios, representation learning, and vision-language modeling.

My current research focus include:

Multispectral perception: designing datasets and architectures that fuse visible and infrared modalities for detection, segmentation, and depth estimation.
Image translation and representation learning: leveraging Vision Foundation Models for RGB-to-Multispectral domain adaptation and spectral translation.
Vision-language and explainable perception: exploring how multimodal models can interpret and describe difficult to understand scenes for safe decision-making.

news

Oct 25, 2025	Our work “IVIFormer: Illumination-Aware Infrared-Visible Image Fusion via Adaptive Domain-Switching Cross Attention”, has been published on ICCV 2025 Workshop Proceedings.
Oct 19, 2025	I organized and served as the Chair of the 2nd Workshop on Multispectral Imaging for Robotics and Automation (MIRA) at the International Conference on Computer Vision (ICCV) 2025.
Apr 10, 2025	We publicly release the RASMD dataset, a large-scale RGB–SWIR benchmark for multispectral perception in adverse weather, available on arXiv and Huggingface.
Dec 30, 2024	Our paper “Short-Wave Infrared (SWIR) Imaging for Robust Material Classification: Overcoming Limitations of Visible Spectrum Data” is is published in Applied Sciences.
Dec 8, 2024	I organized and served as the Chair of the Workshop on Multispectral Imaging for Robotics and Automation (MIRA) at the Asian Conference on Computer Vision (ACCV) 2024.
Sep 25, 2024	Our new preprint, “Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation” is now available on arXiv.
Dec 11, 2023	At the start of 2024, I will begin a new role as a Postdoctoral Researcher at Yonsei University’s Seamless Transportation Lab. Under the guidance of Prof. Shiho Kim, I’ll be working on new challenges of intelligent vehicles and smart mobility.

selected publications

ICCVw

IVIFormer: Illumination-Aware Infrared-Visible Image Fusion via Adaptive Domain-Switching Cross Attention

Park, Incheol, Jin, Youngwan, Nalcakan, Yagiz, Ju, Hyeongjin, Yeo, Sanghyeop, and Kim, Shiho

In Proceedings of the IEEE/CVF International Conference on Computer Vision 2025

Bib LINK

@inproceedings{park2025iviformer,
  abbr = {ICCVw},
  title = {IVIFormer: Illumination-Aware Infrared-Visible Image Fusion via Adaptive Domain-Switching Cross Attention},
  author = {Park, Incheol and Jin, Youngwan and Nalcakan, Yagiz and Ju, Hyeongjin and Yeo, Sanghyeop and Kim, Shiho},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages = {2220--2229},
  year = {2025},
  selected = {true},
  bibtex_show = {true},
  publisher = {ICCVw},
  html = {https://openaccess.thecvf.com/content/ICCV2025W/MIRA/html/Park_IVIFormer_Illumination-Aware_Infrared-Visible_Image_Fusion_via_Adaptive_Domain-Switching_Cross_Attention_ICCVW_2025_paper.html}
}

arXiv

RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions

Jin, Youngwan, Kovac, Michal, Nalcakan, Yagiz, Ju, Hyeongjin, Song, Hanbin, Yeo, Sanghyeop, and Kim, Shiho

arXiv preprint arXiv:2504.07603 2025

Bib LINK

@article{jin2025rasmd,
  abbr = {arXiv},
  title = {RASMD: RGB And SWIR Multispectral Driving Dataset for Robust Perception in Adverse Conditions},
  author = {Jin, Youngwan and Kovac, Michal and Nalcakan, Yagiz and Ju, Hyeongjin and Song, Hanbin and Yeo, Sanghyeop and Kim, Shiho},
  journal = {arXiv preprint arXiv:2504.07603},
  year = {2025},
  selected = {true},
  bibtex_show = {true},
  html = {https://arxiv.org/abs/2504.07603},
  publisher = {arXiv}
}

arXiv

Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation

Jin, Youngwan, Park, Incheol, Song, Hanbin, Ju, Hyeongjin, Nalcakan, Yagiz, and Kim, Shiho

arXiv preprint arXiv:2409.16706 2024

Bib LINK

@article{nalcakan2024pix2next,
  abbr = {arXiv},
  title = {Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation},
  author = {Jin, Youngwan and Park, Incheol and Song, Hanbin and Ju, Hyeongjin and Nalcakan, Yagiz and Kim, Shiho},
  journal = {arXiv preprint arXiv:2409.16706},
  year = {2024},
  selected = {true},
  bibtex_show = {true},
  html = {https://arxiv.org/abs/2409.16706},
  publisher = {arXiv}
}

IEEE

Lane Change Detection with an Ensemble of Image-based and Video-based Deep Learning Models

Nalcakan, Yagiz, and Bastanlar, Yalin

In 2023 Innovations in Intelligent Systems and Applications Conference (ASYU) 2023

Bib LINK

@inproceedings{nalcakan2023asyu,
  abbr = {IEEE},
  author = {Nalcakan, Yagiz and Bastanlar, Yalin},
  booktitle = {2023 Innovations in Intelligent Systems and Applications Conference (ASYU)},
  title = {Lane Change Detection with an Ensemble of Image-based and Video-based Deep Learning Models},
  year = {2023},
  volume = {},
  number = {},
  pages = {1-7},
  selected = {true},
  bibtex_show = {true},
  publisher = {IEEE},
  html = {https://ieeexplore.ieee.org/document/10296634},
  doi = {10.1109/ASYU58738.2023.10296634}
}

SIVP

Cut-in maneuver detection with self-supervised contrastive video representation learning

Nalcakan, Yagiz, and Bastanlar, Yalin

Signal, Image and Video Processing 2023

Bib LINK

@article{nalcakan2023cut,
  abbr = {SIVP},
  title = {Cut-in maneuver detection with self-supervised contrastive video representation learning},
  author = {Nalcakan, Yagiz and Bastanlar, Yalin},
  journal = {Signal, Image and Video Processing},
  pages = {1--9},
  year = {2023},
  selected = {true},
  bibtex_show = {true},
  html = {https://link.springer.com/article/10.1007/s11760-023-02512-3},
  publisher = {Springer}
}

CCIS

Monocular Vision-Based Prediction of Cut-In Manoeuvres with LSTM Networks

Nalcakan, Yagiz, and Bastanlar, Yalin

In Science, Engineering Management and Information Technology 2023

Bib LINK

@inproceedings{10.1007/978-3-031-40395-8_8,
  abbr = {CCIS},
  author = {Nalcakan, Yagiz and Bastanlar, Yalin},
  title = {Monocular Vision-Based Prediction of Cut-In Manoeuvres with LSTM Networks},
  booktitle = {Science, Engineering Management and Information Technology},
  year = {2023},
  publisher = {Springer Nature Switzerland},
  pages = {111--123},
  isbn = {978-3-031-40395-8},
  selected = {true},
  bibtex_show = {true},
  html = {https://link.springer.com/chapter/10.1007/978-3-031-40395-8_8}
}

Overview of Machine Learning Approaches for Wireless Communication

Ensari, Tolga, Nalçakan, Yağız, Günay, Melike, and Yıldız, Eyyüp

In Science, Engineering Management and Information Technology 2019

Bib LINK

@incollection{ensari2019overview,
  title = {Overview of Machine Learning Approaches for Wireless Communication},
  author = {Ensari, Tolga and Nal{\c{c}}akan, Ya{\u{g}}{\i}z and G{\"u}nay, Melike and Y{\i}ld{\i}z, Eyy{\"u}p},
  booktitle = {Next-Generation Wireless Networks Meet Advanced Machine Learning Applications},
  pages = {123--140},
  year = {2019},
  publisher = {IGI Global},
  selected = {true},
  bibtex_show = {true},
  html = {https://www.igi-global.com/chapter/overview-of-machine-learning-approaches-for-wireless-communication/221429}
}

IEEE

Automatic HTML code generation from mock-up images using machine learning techniques

Aşıroğlu, Batuhan, Mete, Büşta Rümeysa, Yıldız, Eyyüp, Nalçakan, Yağız, Sezen, Alper, Dağtekin, Mustafa, and Ensari, Tolga

In 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT) 2019

Bib LINK

@inproceedings{acsirouglu2019automatic,
  abbr = {IEEE},
  title = {Automatic HTML code generation from mock-up images using machine learning techniques},
  author = {A{\c{s}}{\i}ro{\u{g}}lu, Batuhan and Mete, B{\"u}{\c{s}}ta R{\"u}meysa and Y{\i}ld{\i}z, Eyy{\"u}p and Nal{\c{c}}akan, Ya{\u{g}}{\i}z and Sezen, Alper and Da{\u{g}}tekin, Mustafa and Ensari, Tolga},
  booktitle = {2019 Scientific Meeting on Electrical-Electronics \& Biomedical Engineering and Computer Science (EBBT)},
  pages = {1--4},
  year = {2019},
  organization = {Ieee},
  selected = {true},
  bibtex_show = {true},
  html = {https://ieeexplore.ieee.org/abstract/document/8741736}
}

Decision of Neural Networks Hyperparameters with a Population-based Algorithm

Nalçakan, Yağız, and Ensari, Tolga

In The Fourth International Conference on Machine Learning, Optimization, and Data Science 2018

Bib LINK

@inproceedings{nalcakan2018decision,
  title = {Decision of Neural Networks Hyperparameters with a Population-based Algorithm},
  author = {Nal{\c{c}}akan, Ya{\u{g}}{\i}z and Ensari, Tolga},
  booktitle = {The Fourth International Conference on Machine Learning, Optimization, and Data Science},
  volume = {11331},
  year = {2018},
  selected = {true},
  bibtex_show = {true},
  html = {https://link.springer.com/chapter/10.1007/978-3-030-13709-0_23}
}

Digital Data Forgetting: A Machine Learning Approach

Günay, Melike, Yıldız, Eyyüp, Nalçakan, Yağız, Aşıroğlu, B, Zencirli, A, Mete, B, and Ensari, Tolga

In 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) 2018

Bib LINK

@inproceedings{gunay2018digital,
  title = {Digital Data Forgetting: A Machine Learning Approach},
  author = {G{\"u}nay, Melike and Y{\i}ld{\i}z, Eyy{\"u}p and Nal{\c{c}}akan, Ya{\u{g}}{\i}z and A{\c{s}}{\i}ro{\u{g}}lu, B and Zencirli, A and Mete, B and Ensari, Tolga},
  booktitle = {2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)},
  pages = {1--4},
  year = {2018},
  organization = {DOI: 10.1109/ISMSIT.2018.8567046},
  selected = {true},
  bibtex_show = {true},
  html = {https://doi.org/10.1109/ISMSIT.2018.8567046}
}

service

Journal Reviewer:

Elsevier Information Fusion (INFFUS)
Elsevier Computer Vision and Image Understanding (CVIU)
Elsevier Expert Systems with Applications (ESWA)
IEEE Transactions on Intelligent Vehicles (T-IV)
IEEE Transactions on Intelligent Transportation Systems (T-ITS)

Conference Reviewer:

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)
IEEE International Conference on Computer Vision (ICCV)
AAAI Conference on Artificial Intelligence (AAAI)
IEEE International Conference on Intelligent Transportation Systems (ITSC)
IEEE Intelligent Vehicles Symposium (IV)

Program Committee:

Chair, ICCV 2025 Workshop on Multispectral Imaging for Robotics and Automation (MIRA)
Chair, ACCV 2024 Workshop on Multispectral Imaging for Robotics and Automation (MIRA)