Search Results - "Tefas, Anastasios"

Training Lightweight Deep Convolutional Neural Networks Using Bag-of-Features Pooling by Passalis, Nikolaos, Tefas, Anastasios

“…Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs…”
Get full text

Continuous drone control using deep reinforcement learning for frontal view person shooting by Passalis, Nikolaos, Tefas, Anastasios

“…Drones, also known as unmanned aerial vehicles, can be used to aid various aerial cinematography tasks. However, using drones for aerial cinematography…”
Get full text

Variance-preserving deep metric learning for content-based image retrieval by Passalis, Nikolaos, Iosifidis, Alexandros, Gabbouj, Moncef, Tefas, Anastasios

“…•Discriminative metric learning can remove valuable information from a representation.•A regularized discriminative deep metric learning method is…”
Get full text

Neuromorphic Silicon Photonics and Hardware-Aware Deep Learning for High-Speed Inference by Moralis-Pegios, Miltiadis, Mourgias-Alexandris, George, Tsakyridis, Apostolos, Giamougiannis, George, Totovic, Angelina, Dabos, George, Passalis, Nikolaos, Kirtas, Manos, Rutirawut, T., Gardes, F. Y., Tefas, Anastasios, Pleros, Nikos

“…The relentless growth of Artificial Intelligence (AI) workloads has fueled the drive towards non-Von Neuman architectures and custom computing hardware…”
Get full text

Transferring trading strategy knowledge to deep learning models by Tsantekidis, Avraam, Tefas, Anastasios

“…Trading strategies are constantly being employed in the financial markets in order to increase consistency, reduce human errors of judgment and boost the…”
Get full text

Exploiting multiplex data relationships in Support Vector Machines by Mygdalis, Vasileios, Tefas, Anastasios, Pitas, Ioannis

“…•Introducing multiplex data relationships to the SVM optimization process.•The proposed method exploits and extends the findings of Multiple Kernel Learning…”
Get full text

Multi-view action recognition based on action volumes, fuzzy distances and cluster discriminant analysis by Iosifidis, Alexandros, Tefas, Anastasios, Pitas, Ioannis

“…In this paper, we present a view-independent action recognition method exploiting a low computational-cost volumetric action representation. Binary images…”
Get full text

Multi-view human movement recognition based on fuzzy distances and linear discriminant analysis by Iosifidis, Alexandros, Tefas, Anastasios, Nikolaidis, Nikolaos, Pitas, Ioannis

“…In this paper, a novel multi-view human movement recognition method is presented. A novel representation of multi-view human movement videos is proposed that…”
Get full text

Dynamic action recognition based on dynemes and Extreme Learning Machine by Iosifidis, Alexandros, Tefas, Anastasios, Pitas, Ioannis

“…► Action recognition is performed by a novel dynamic classification scheme. ► Dynamic classification involves determination of the optimal training data and…”
Get full text

Visual Object Tracking Based on Local Steering Kernels and Color Histograms by Zoidi, O., Tefas, A., Pitas, I.

“…In this paper, we propose a visual object tracking framework, which employs an appearance-based representation of the target object, based on local steering…”
Get full text

Forecasting Financial Time Series Using Robust Deep Adaptive Input Normalization by Passalis, Nikolaos, Kanniainen, Juho, Gabbouj, Moncef, Iosifidis, Alexandros, Tefas, Anastasios

“…Deep Learning provided powerful tools for forecasting financial time series data. However, despite the success of these approaches on many challenging…”
Get full text

Analog nanophotonic computing going practical: silicon photonic deep learning engines for tiled optical matrix multiplication with dynamic precision by Giamougiannis, George, Tsakyridis, Apostolos, Moralis-Pegios, Miltiadis, Pappas, Christos, Kirtas, Manos, Passalis, Nikolaos, Lazovsky, David, Tefas, Anastasios, Pleros, Nikos

“…Analog photonic computing comprises a promising candidate for accelerating the linear operations of deep neural networks (DNNs), since it provides ultrahigh…”
Get full text

Activity-Based Person Identification Using Fuzzy Representation and Discriminant Learning by Iosifidis, A., Tefas, A., Pitas, I.

“…In this paper, a novel view invariant person identification method based on human activity information is proposed. Unlike most methods proposed in the…”
Get full text

Machine Learning for Forecasting Mid-Price Movements Using Limit Order Book Data by Nousi, Paraskevi, Tsantekidis, Avraam, Passalis, Nikolaos, Ntakaris, Adamantios, Kanniainen, Juho, Tefas, Anastasios, Gabbouj, Moncef, Iosifidis, Alexandros

“…Forecasting the movements of stock prices is one of the most challenging problems in financial markets analysis. In this paper, we use machine learning (ML)…”
Get full text

Attention-Based Neural Bag-of-Features Learning for Sequence Data by Tran, Dat Thanh, Passalis, Nikolaos, Tefas, Anastasios, Gabbouj, Moncef, Iosifidis, Alexandros

“…In this paper, we propose 2D-Attention (2DA), a generic attention formulation for sequence data, which acts as a complementary computation block that can…”
Get full text

Photonic neural networks and optics-informed deep learning fundamentals by Tsakyridis, Apostolos, Moralis-Pegios, Miltiadis, Giamougiannis, George, Kirtas, Manos, Passalis, Nikolaos, Tefas, Anastasios, Pleros, Nikos

“…The recent explosive compute growth, mainly fueled by the boost of artificial intelligence (AI) and deep neural networks (DNNs), is currently instigating the…”
Get full text

WDM equipped universal linear optics for programmable neuromorphic photonic processors by Totovic, Angelina, Pappas, Christos, Kirtas, Manos, Tsakyridis, Apostolos, Giamougiannis, George, Passalis, Nikolaos, Moralis-Pegios, Miltiadis, Tefas, Anastasios, Pleros, Nikos

“…Abstract Non-von-Neumann computing architectures and deep learning training models have sparked a new computational era where neurons are forming the main…”
Get full text

Weighted Piecewise LDA for Solving the Small Sample Size Problem in Face Verification by Kyperountas, M., Tefas, A., Pitas, I.

“…A novel algorithm that can be used to boost the performance of face-verification methods that utilize Fisher's criterion is presented and evaluated. The…”
Get full text

Deep convolutional learning for Content Based Image Retrieval by Tzelepi, Maria, Tefas, Anastasios

“…In this paper we propose a model retraining method for learning more efficient convolutional representations for Content Based Image Retrieval. We employ a…”
Get full text

Forecasting Stock Prices from the Limit Order Book Using Convolutional Neural Networks by Tsantekidis, Avraam, Passalis, Nikolaos, Tefas, Anastasios, Kanniainen, Juho, Gabbouj, Moncef, Iosifidis, Alexandros

“…In today's financial markets, where most trades are performed in their entirety by electronic means and the largest fraction of them is completely automated,…”
Get full text