ARISTOTLE UNIVERSITY OF THESSALONIKI

research

∙ 09/06/2021

Graph Attention Layer Evolves Semantic Segmentation for Road Pothole Detection: A Benchmark and Algorithms

Existing road pothole detection approaches can be classified as computer...

Rui Fan, et al. ∙

research

∙ 05/17/2020

Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator

Over the past decade, significant efforts have been made to improve the ...

Rui Fan, et al. ∙

research

∙ 12/04/2021

Ablation study of self-supervised learning for image classification

This project focuses on the self-supervised training of convolutional ne...

Ilias Papastratis, et al. ∙

research

∙ 12/19/2020

Rethinking Road Surface 3D Reconstruction and Pothole Detection: From Perspective Transformation to Disparity Map Segmentation

Potholes are one of the most common forms of road damage, which can seve...

Rui Fan, et al. ∙

research

∙ 11/30/2018

Style Decomposition for Improved Neural Style Transfer

Universal Neural Style Transfer (NST) methods are capable of performing ...

Paraskevas Pegios, et al. ∙

research

∙ 06/11/2019

Bag of Color Features For Color Constancy

In this paper, we propose a novel color constancy approach, called Bag o...

Firas Laakom, et al. ∙

research

∙ 08/02/2019

Pothole Detection Based on Disparity Transformation and Road Surface Modeling

Pothole detection is one of the most important tasks for road maintenanc...

Rui Fan, et al. ∙

research

∙ 06/06/2022

VPIT: Real-time Embedded Single Object 3D Tracking Using Voxel Pseudo Images

In this paper, we propose a novel voxel-based 3D single object tracking ...

Illia Oleksiienko, et al. ∙

research

∙ 07/28/2017

Learning to Teach Reinforcement Learning Agents

In this article we study the transfer learning model of action advice un...

Anestis Fachantidis, et al. ∙

research

∙ 12/25/2015

Inducing Generalized Multi-Label Rules with Learning Classifier Systems

In recent years, multi-label classification has attracted a significant ...

Fani A. Tzima, et al. ∙

research

∙ 06/26/2017

Learning Local Feature Aggregation Functions with Backpropagation

This paper introduces a family of local feature aggregation functions an...

Angelos Katharopoulos, et al. ∙

research

∙ 02/24/2017

Measuring #GamerGate: A Tale of Hate, Sexism, and Bullying

Over the past few years, online aggression and abusive behaviors have oc...

Despoina Chatzakou, et al. ∙

research

∙ 07/25/2017

Learning Bag-of-Features Pooling for Deep Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are well established models capable...

Nikolaos Passalis, et al. ∙

research

∙ 03/06/2016

An Argument-based Creative Assistant for Harmonic Blending

Conceptual blending is a powerful tool for computational creativity wher...

Maximos Kaliakatsos-Papakostas, et al. ∙

research

∙ 12/19/2016

Photo-Quality Evaluation based on Computational Aesthetics: Review of Feature Extraction Techniques

Researchers try to model the aesthetic quality of photographs into low a...

Dimitris Spathis, et al. ∙

research

∙ 11/11/2015

Granger Causality in Multi-variate Time Series using a Time Ordered Restricted Vector Autoregressive Model

Granger causality has been used for the investigation of the inter-depen...

Elsa Siggiridou, et al. ∙

research

∙ 04/23/2013

The Stochastic Gradient Descent for the Primal L1-SVM Optimization Revisited

We reconsider the stochastic (sub)gradient approach to the unconstrained...

Constantinos Panagiotakopoulos, et al. ∙

research

∙ 05/08/2015

Dense Distributions from Sparse Samples: Improved Gibbs Sampling Parameter Estimators for LDA

We introduce a novel approach for estimating Latent Dirichlet Allocation...

Yannis Papanikolaou, et al. ∙

research

∙ 10/10/2011

Open Source Software: How Can Design Metrics Facilitate Architecture Recovery?

Modern software development methodologies include reuse of open source c...

Eleni Constantinou, et al. ∙

research

∙ 01/11/2013

Backward-in-Time Selection of the Order of Dynamic Regression Prediction Model

We investigate the optimal structure of dynamic regression models used i...

Ioannis Vlachos, et al. ∙

research

∙ 07/12/2011

A Variation of the Box-Counting Algorithm Applied to Colour Images

The box counting method for fractal dimension estimation had not been ap...

N. S. Nikolaidis, et al. ∙

research

∙ 10/20/2017

Local Word Vectors Guiding Keyphrase Extraction

Automated keyphrase extraction is a fundamental textual information proc...

Eirini Papagiannopoulou, et al. ∙

research

∙ 12/07/2017

Core Discovery in Hidden Graphs

Massive network exploration is an important research direction with many...

Panagiotis Strouthopoulos, et al. ∙

research

∙ 11/17/2017

Metric Map Merging using RFID Tags & Topological Information

A map merging component is crucial for the proper functionality of a mul...

Emmanouil Tsardoulias, et al. ∙

research

∙ 07/18/2017

Impact and Productivity of PhD Graduates of Computer Science/Engineering Departments of Hellenic Universities

This article presents an anatomy of PhD programmes in Hellenic universit...

Dimitrios Katsaros, et al. ∙

research

∙ 09/12/2017

Skyline Queries in O(1) time?

The skyline of a set P of points (SKY(P)) consists of the "best" points ...

Spyros Sioutas, et al. ∙

research

∙ 09/07/2017

MK-fuzzy Automata and MSO Logics

We introduce MK-fuzzy automata over a bimonoid K which is related to the...

Manfred Droste, et al. ∙

research

∙ 01/13/2018

Secure Communications in NOMA System: Subcarrier Assignment and Power Allocation

Secure communication is a promising technology for wireless networks bec...

Haijun Zhang, et al. ∙

research

∙ 02/01/2018

A Unified Deep Learning Architecture for Abuse Detection

Hate speech, offensive language, sexism, racism and other types of abusi...

Antigoni-Maria Founta, et al. ∙

research

∙ 03/15/2018

Resource Allocation in NOMA based Fog Radio Access Networks

In the wake of growth in intelligent mobile devices and wide usage of ba...

H. Zhang, et al. ∙

research

∙ 03/24/2018

Physical Layer Security in the Presence of Interference

We evaluate and quantify the joint effect of fading and multiple interfe...

Dimitrios S. Karas, et al. ∙

research

∙ 03/24/2018

Spectrum Sensing with Multiple Primary Users over Fading Channels

We investigate the impact of multiple primary users (PUs) and fading on ...

Alexandros-Apostolos A. Boulogeorgos, et al. ∙

research

∙ 03/28/2018

Probabilistic Knowledge Transfer for Deep Representation Learning

Knowledge Transfer (KT) techniques tackle the problem of transferring th...

Nikolaos Passalis, et al. ∙

research

∙ 05/06/2018

SqueezeJet: High-level Synthesis Accelerator Design for Deep Convolutional Neural Networks

Deep convolutional neural networks have dominated the pattern recognitio...

Panagiotis G. Mousouliotis, et al. ∙

research

∙ 06/26/2018

Process Network Models for Embedded System Design Based on the Real-Time BIP Execution Engine

Existing model-based processes for embedded real-time systems support th...

Fotios Gioulekas, et al. ∙

research

∙ 06/26/2018

Model-Based Design of Energy-Efficient Applications for IoT Systems

A major challenge that is currently faced in the design of applications ...

Alexios Lekidis, et al. ∙

research

∙ 07/05/2018

Deep Reinforcement Learning for Doom using Unsupervised Auxiliary Tasks

Recent developments in deep reinforcement learning have enabled the crea...

Georgios Papoudakis, et al. ∙

research

∙ 07/30/2018

Making Classifier Chains Resilient to Class Imbalance

Class imbalance is an intrinsic characteristic of multi-label data. Most...

Bin Liu, et al. ∙

research

∙ 08/10/2018

Unsupervised Keyphrase Extraction Based on Outlier Detection

We propose a novel unsupervised keyphrase extraction approach based on o...

Eirini Papagiannopoulou, et al. ∙

research

∙ 09/17/2018

Span error bound for weighted SVM with applications in hyperparameter selection

Weighted SVM (or fuzzy SVM) is the most widely used SVM variant owning i...

Ioannis Sarafis, et al. ∙

research

∙ 09/19/2018

Machine Learning for Forecasting Mid Price Movement using Limit Order Book Data

Forecasting the movements of stock prices is one the most challenging pr...

Paraskevi Nousi, et al. ∙

research

∙ 10/23/2018

Using Deep Learning for price prediction by exploiting stationary limit order book features

The recent surge in Deep Learning (DL) research of the past decade has s...

Avraam Tsantekidis, et al. ∙

research

∙ 11/12/2018

A Framework of Transfer Learning in Object Detection for Embedded Systems

Transfer learning is one of the subjects undergoing intense study in the...

Ioannis Athanasiadis, et al. ∙

research

∙ 12/29/2018

Interference-Free Transceiver Design and Signal Detection for Ambient Backscatter Communication Systems over Frequency-Selective Channels

In this letter, we study the ambient backscatter communication systems o...

Chong Zhang, et al. ∙

research

∙ 01/05/2019

A Unified Spatial Framework for UAV-aided MmWave Networks

In this paper, we propose a unified three-dimensional (3D) spatial frame...

Wenqiang Yi, et al. ∙

research

∙ 01/13/2019

Longest Common Subsequence on Weighted Sequences

We consider the general problem of the Longest Common Subsequence (LCS) ...

Evangelos Kipouridis, et al. ∙

research

∙ 01/16/2019

Deep Supervised Hashing leveraging Quadratic Spherical Mutual Information for Content-based Image Retrieval

Several deep supervised hashing techniques have been proposed to allow f...

Nikolaos Passalis, et al. ∙

research

∙ 01/24/2019

Temporal Logistic Neural Bag-of-Features for Financial Time series Forecasting leveraging Limit Order Book Data

Time series forecasting is a crucial component of many important applica...

Nikolaos Passalis, et al. ∙

research

∙ 02/02/2019

RELINE: Point-of-Interest Recommendations using Multiple Network Embeddings

The rapid growth of users' involvement in Location-Based Social Networks...

Giannis Christoforidis, et al. ∙

research

∙ 02/08/2019

Software-Defined FPGA Accelerator Design for Mobile Deep Learning Applications

Recently, the field of deep learning has received great attention by the...

Panagiotis G. Mousouliotis, et al. ∙

ARISTOTLE UNIVERSITY OF THESSALONIKI

Featured Researchers