Nikos Komodakis – Institute of Applied and Computational Mathematics

Nikos Komodakis holds the position of Associate Professor at the Computer Science Department, University of Crete. He is also affiliated with the Institute of Applied & Computational Mathematics, FORTH, and is a researcher at the Archimedes Center for Research in Artificial Intelligence. Previously, he served as an Associate Professor at Ecole des Ponts ParisTech and held roles as a research scientist at the French National Centre for Scientific Research (CNRS) and a visiting Professor at Ecole Normale Superieure de Cachan. His research focuses on Computer Vision/Image Analysis, Machine Learning, and Artificial Intelligence. Furthermore, he contributes as an Editorial Board Member/Associate Editor for journals like Computer Vision and Image Understanding, International Journal of Computer Vision, and Computational Intelligence Journal.

Contact Info

First Name

NIKOS

Last Name

KOMODAKIS

komod@csd.uoc.gr

curriculum-vitae.pdf

Webpage

https://www.csd.uoc.gr/~komod/

Address

Computer Science Department, University of Crete, Voutes Campus, 700 13 Heraklion, Crete, Greece

Phone

+30 2810 393547

PUBLICATIONS

Selected Publications

Differentiable Gamma Index-Based Loss Functions: Accelerating Monte-Carlo Radiotherapy Dose Simulation, S Martinot, N Komodakis, M Vakalopoulou, N Bus, C Robert, E Deutsch, … (2023), International Conference on Information Processing in Medical Imaging, 485-496.

PO-1802 Deep Particles Embedding: accelerating Monte-Carlo dose simulations, S Martinot, N Komodakis, M Vakalopoulou, N Bus, C Robert, E Deutsch, … (2023), Radiotherapy and Oncology 182, S1526-S1527.

What to hide from your students: Attention-guided masked image modeling, I Kakogeorgiou, S Gidaris, B Psomas, Y Avrithis, A Bursuc, K Karantzalos, … (2022), European Conference on Computer Vision, 300-318.

Self-supervised learning for medieval handwriting identification: A case study from the Vatican Apostolic Library, L Lastilla, S Ammirati, D Firmani, N Komodakis, P Merialdo, … (2022), Information Processing & Management 59 (3), 102875.

MARE: Self-supervised multi-attention REsu-Net for semantic segmentation in remote sensing, V Marsocci, S Scardapane, N Komodakis (2021), Remote Sensing 13 (16), 3275.

Exploring weight symmetry in deep neural networks, SX Hu, S Zagoruyko, N Komodakis (2019), Computer Vision and Image Understanding 187, 102786.

Deep tone mapping operator for high dynamic range images, A Rana, P Singh, G Valenzise, F Dufaux, N Komodakis, A Smolic (2019), IEEE Transactions on Image Processing 29, 1285-1298.

RESEARCH

Research Interests

My research interests span the areas of deep learning, computer vision, machine learning, medical image analysis and artificial intelligence.

In a nutshell, the goal of my research is to develop efficient, scalable and mathematically well-grounded algorithms that are capable of analyzing and extracting (semantic) information from various types of visual data (be it static natural images, video, medical image data etc.).