ΕΛ EN
Home | People | Chatzis, Sotirios P.
143
Scholarly Works
23%
OA Ratio
39%
Collaborative Ratio
Scholar

Chatzis, Sotirios P.

Associate Professor

Department of Electrical Engineering, Computer Engineering and Informatics

26
H-index (Scopus)
3978
Scholar Citations

Scholarly Works

Research Output

Recent Publications

Predicting ship hull flow-field distributions using a soft-constrained ANN model

Publishing year: 2026
Journal article
2026, Volume 18
Web of Science

Gaze Prediction in Virtual Reality Without Eye Tracking Using Visual and Head Motion Cues

C Petrou, H Partaourides, A Balomenos, Y Kopsinis, S Chatzis
Publishing year: 2025
Book
International Symposium on Visual Computing, 399-410, 2025, 2025
Google Scholar
Pages 399-410
Gaze prediction plays a critical role in Virtual Reality (VR) applications by reducing sensor-induced latency and enabling computationally demanding techniques such as foveated rendering, which rely on anticipating user attention. However, direct eye tracking is often unavailable due to hardware limitations or privacy concerns. To address this, we present a novel gaze prediction framework that combines Head-Mounted Display (HMD) motion signals with visual saliency cues derived from video frames. Our method employs UniSal, a lightweight saliency encoder, to extract visual features, which are then fused with HMD motion data and processed through a time-series prediction module. We evaluate two lightweight architectures, TSMixer and LSTM, for forecasting future gaze directions. Experiments on the EHTask dataset, along with deployment on commercial VR hardware, show that our approach consistently …

CMAD: Conditional Modeling-Adapter Diffusion for Video Super-Resolution

C Wang, J Nie, Z He, S Chatzis
Publishing year: 2025
Book
International Symposium on Visual Computing, 111-124, 2025, 2025
Google Scholar
Pages 111-124
Video super-resolution (VSR) aims to restore high-resolution videos from low-resolution inputs, enhancing visual quality under real-world degradation. Existing diffusion-based VSR methods often rely on specially designed network architectures or text prompts as conditional inputs, which limits their flexibility and applicability—especially in scenarios where explicit text descriptions are unavailable. To tackle this challenge, we propose a Conditional Modeling ADapter that enables zero-modification reuse of pre-trained text-to-video diffusion models for the VSR task, called CMAD. The adapter transforms low-resolution video features into pseudo-text tokens via a pre-trained Vision Transformer (ViT) and a lightweight adapter module, allowing these features to be injected as encoder hidden states, which serve as the main conditioning interface within the diffusion model. Unlike previous methods that require …

Transformers with stochastic competition for tabular data modelling

A Voskou, C Christoforou, S Chatzis
Publishing year: 2024
Journal article
arXiv preprint arXiv:2407.13238, 2024, 2024
Google Scholar
Despite the prevalence and significance of tabular data across numerous industries and fields, it has been relatively underexplored in the realm of deep learning. Even today, neural networks are often overshadowed by techniques such as gradient boosted decision trees (GBDT). However, recent models are beginning to close this gap, outperforming GBDT in various setups and garnering increased attention in the field. Inspired by this development, we introduce a novel stochastic deep learning model specifically designed for tabular data. The foundation of this model is a Transformer-based architecture, carefully adapted to cater to the unique properties of tabular data through strategic architectural modifications and leveraging two forms of stochastic competition. First, we employ stochastic "Local Winner Takes All" units to promote generalization capacity through stochasticity and sparsity. Second, we introduce a novel embedding layer that selects among alternative linear embedding layers through a mechanism of stochastic competition. The effectiveness of the model is validated on a variety of widely-used, publicly available datasets. We demonstrate that, through the incorporation of these elements, our model yields high performance and marks a significant advancement in the application of deep learning to tabular data.

Stochastic Deep Networks with Linear Competing Units for Transfer Learning

Chatzis, Sotirios P., Kalais, Konstantinos
Publishing year: 2024
Thesis Repository
Deep Learning (DL) has become the preferred approach to addressing various challenging machine learning (MLe) tasks, like computer vision, natural language processing, and speech recognition. Deep Neural Networks (DNN's) have achieved superior performance in those tasks compared to traditional MLe methods. However, they entail a huge number of weights causing them to make over-confident predictions, that may reduce their generalization capacity in hard problems, e.g. a Meta-Learning (ML) scenario. To mitigate this issue, researchers have applied Bayesian modeling to DNN's, where they employ Bayesian Neural Networks (BNN's) with more robust and tractable estimates of uncertainty in a model's predictions. That way, we can build safer MLe systems in safety-critical applications, such as healthcare, video recognition, and autonomous vehicle control. DL models trained to solve a single task suffer from a common drawback: they cannot combine data from diverse tasks in order to learn new tasks in a future training round. Such models often require extensive training and data collection for each task individually, which can be time-consuming and data-intensive. This limitation has given rise to the importance of research in ML. This field aims to address these shortcomings by developing methods that allow existing models to efficiently learn from and adapt quickly to new tasks, by leveraging knowledge gained from previous tasks. Therefore, ML methods aim to make models more capable...

Deep Transformer Neural Networks with Stochastic Competition

Chatzis, Sotirios P., Voskou, Andreas
Publishing year: 2024
Thesis Repository
Transformers have become one of the most successful architectures in deep learning, experiencing a steady rise in popularity. These advanced networks have revolutionized the field of Natural Language Processing (NLP) and are extending their influence into new domains within artificial intelligence and beyond. The recent rise of large language models, fundamentally reliant on Transformer architectures, highlights their effectiveness and underscores their transformative impact. This thesis delves into exploring further capabilities of this deep learning framework by incorporating stochastic methodologies as an essential component of Transformer networks. Our primary focus is on leveraging stochastic competition techniques, proven to be highly advantageous in various contexts, as the cornerstone for developing highperforming models. Instead of focusing on the extensively researched application areas such as NLP, our research pivots to exploring two distinct and significantly different fields: i) Sign Language Translation and ii) Tabular Data Modeling.

143
Unique publications
23.1%
Open access (33 publications; 27 without information)
38.5%
With other institutions (55 publications; 30 without information)

H-Index Reports

Index type Scopus Google Scholar Web of Science
H-index 26 35 1
H5-index 8 12 1
H10-index 19 24 1

Publications per year and source

No description yet.
Faculty
Faculty of Engineering and Technology
Department
Department of Electrical Engineering, Computer Engineering and Informatics
Title
Associate Professor