A
Anastasios Doulamis
Researcher at National Technical University of Athens
Publications - 395
Citations - 8217
Anastasios Doulamis is an academic researcher from National Technical University of Athens. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 34, co-authored 355 publications receiving 5794 citations. Previous affiliations of Anastasios Doulamis include Technical University of Crete & University of Crete.
Papers
More filters
Journal ArticleDOI
Deep Learning for Computer Vision: A Brief Review.
TL;DR: A brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders are provided.
Proceedings ArticleDOI
Deep supervised learning for hyperspectral data classification through convolutional neural networks
TL;DR: This work proposes a deep learning based classification method that hierarchically constructs high-level features in an automated way and exploits a Convolutional Neural Network to encode pixels' spectral and spatial information and a Multi-Layer Perceptron to conduct the classification task.
Journal ArticleDOI
A fuzzy video content representation for video summarization and content-based retrieval
TL;DR: A multidimensional fuzzy histogram is constructed for each video frame based on a collection of appropriate features, extracted using video sequence analysis techniques, which is applied both for video summarization, in the context of a content- based sampling algorithm, and for content-based indexing and retrieval.
Proceedings ArticleDOI
Deep Convolutional Neural Networks for efficient vision based tunnel inspection
Konstantinos Makantasis,Eftychios Protopapadakis,Anastasios Doulamis,Nikolaos Doulamis,Constantinos Loupos +4 more
TL;DR: A fully automated tunnel assessment approach is proposed; using the raw input from a single monocular camera the authors hierarchically construct complex features, exploiting the advantages of deep learning architectures, and achieves very fast predictions due to the feedforward nature of Convolutional Neural Networks and Multi-Layer Perceptrons.
Journal ArticleDOI
An adaptable neural-network model for recursive nonlinear traffic prediction and modeling of MPEG video sources
TL;DR: It is shown that the proposed adaptable neural-network architecture simulates a recursive nonlinear autoregressive model (RNAR) similar to the notation used in the linear case, and presents low computational complexity and high efficiency in tracking traffic rates in contrast to conventional retraining schemes.