activity
20182021
collaborators

5 papers

cs.LG2021

Rank-R FNN: A Tensor-Based Learning Model for High-Order Data Classification

Konstantinos Makantasis, Alexandros Georgogiannis, Athanasios Voulodimos +3

An increasing number of emerging applications in data science and engineering are based on multidimensional and structurally rich data. The irregularities, however, of high-dimensi…

cs.CV2020

Pixel-level Corrosion Detection on Metal Constructions by Fusion of Deep Learning Semantic and Contour Segmentation

Iason Katsamenis, Eftychios Protopapadakis, Anastasios Doulamis +2

Corrosion detection on metal constructions is a major challenge in civil engineering for quick, safe and effective inspection. Existing image analysis approaches tend to place boun…

cs.LG2020

Space-Time Domain Tensor Neural Networks: An Application on Human Pose Classification

Konstantinos Makantasis, Athanasios Voulodimos, Anastasios Doulamis +2

Recent advances in sensing technologies require the design and development of pattern recognition models capable of processing spatiotemporal data efficiently. In this study, we pr…

cs.LG2019

Common Mode Patterns for Supervised Tensor Subspace Learning

Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis +1

In this work we propose a method for reducing the dimensionality of tensor objects in a binary classification framework. The proposed Common Mode Patterns method takes into conside…

cs.LG2018

Tensor-based Nonlinear Classifier for High-Order Data Analysis

Konstantinos Makantasis, Anastasios Doulamis, Nikolaos Doulamis +2

In this paper we propose a tensor-based nonlinear model for high-order data classification. The advantages of the proposed scheme are that (i) it significantly reduces the number o…