147 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Christos Diou2 profiles9 · h 9
- Aristotelis Ballas6 · h 6
- Georgios Th. Papadopoulos2 profiles6 · h 6
- Iraklis Varlamis2 profiles6 · h 29
- Ioannis Mademlis5 · h 6
- K. Tserpes4 · h 40
- T. Varvarigou4 · h 37
- Vasileios Papapanagiotou4 · h 12
- A. Alsalemi3 · h 27
- A. Amira3 · h 50
- Adamantia Anna Rebolledo Chrysochoou3 · h 3
- B. Kostopoulos3 · h 1
- National Technical University of AthensGR7 papers
- Vrije Universiteit BrusselBE4 papers
- Aristotle University of ThessalonikiGR3 papers
- Centre for Research and Technology HellasGR3 papers
- De Montfort UniversityGB3 papers
- National and Kapodistrian University of AthensGR3 papers
- Qatar UniversityQA3 papers
- University of the AegeanGR3 papers
- Athens University of Economics and BusinessGR2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- École de Technologie SupérieureCA2 papers
- Frontier Science Foundation-HellasGR2 papers
11 papers · 1 filter
Reducing Inference Energy Consumption Using Dual Complementary CNNs
Michail Kinnas, John Violos, Ioannis Kompatsiaris +1
Energy efficiency of Convolutional Neural Networks (CNNs) has become an important area of research, with various strategies being developed to minimize the power consumption of the…
FaceX: Understanding Face Attribute Classifiers through Summary Model Explanations
Ioannis Sarridis, Christos Koutlis, Symeon Papadopoulos +1
EXplainable Artificial Intelligence (XAI) approaches are widely applied for identifying fairness issues in Artificial Intelligence (AI) systems. However, in the context of facial a…
Entity Extraction from High-Level Corruption Schemes via Large Language Models
Panagiotis Koletsis, Panagiotis-Konstantinos Gemos, Christos Chronis +3
The rise of financial crime that has been observed in recent years has created an increasing concern around the topic and many people, organizations and governments are more and mo…
The Stable Model Semantics for Higher-Order Logic Programming
Bart Bogaerts, Angelos Charalambidis, Giannos Chatziagapis +3
We propose a stable model semantics for higher-order logic programs. Our semantics is developed using Approximation Fixpoint Theory (AFT), a powerful formalism that has successfull…
A Category-Theoretic Perspective on Higher-Order Approximation Fixpoint Theory
Samuele Pollaci, Babis Kostopoulos, Marc Denecker +1
Approximation Fixpoint Theory (AFT) is an algebraic framework designed to study the semantics of non-monotonic logics. Despite its success, AFT is not readily applicable to higher-…
Local Limit Theorems for -Multinomial and Multiple Heine Distributions
Malvina Vamvakari
In this work we establish local limit theorems for q-multinomial and multiple Heine distributions. Specifically, the pointwise convergence of the q-multinomial distribution of the…
Illicit object detection in X-ray images using Vision Transformers
Jorgen Cani, Ioannis Mademlis, Adamantia Anna Rebolledo Chrysochoou +1
Illicit object detection is a critical task performed at various high-security locations, including airports, train stations, subways, and ports. The continuous and tedious work of…
Urgent Edge Computing
Patrizio Dazzi, Luca Ferrucci, Marco Danelutto +6
This position paper introduces Urgent Edge Computing (UEC) as a paradigm shift addressing the evolving demands of time-sensitive applications in distributed edge environments, in t…
Self-supervised visual learning in the low-data regime: a comparative evaluation
Sotirios Konstantakos, Jorgen Cani, Ioannis Mademlis +4
Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a 'pretext task' tha…
Pseudo-Random Generator based on a Photonic Neuromorphic Physical Unclonable Function
Dimitris Dermanis, Panagiotis Rizomiliotis, Adonis Bogris +1
In this work we provide numerical results concerning a silicon-on-insulator photonic neuromorphic circuit configured as a physical unclonable function. The proposed scheme is enhan…
Rapid post-disaster infrastructure damage characterisation enabled by remote sensing and deep learning technologies -- a tiered approach
Nadiia Kopiika, Andreas Karavias, Pavlos Krassakis +6
Critical infrastructure, such as transport networks and bridges, are systematically targeted during wars and suffer damage during extensive natural disasters because it is vital fo…