82 citations · 356 across the 60 of their papers we have counts for
9 papers · 1 filter
Detecting Adversarial Examples in Convolutional Neural Networks
Stefanos Pertigkiozoglou, Petros Maragos
The great success of convolutional neural networks has caused a massive spread of the use of such models in a large variety of Computer Vision applications. However, these models a…
SUSiNet: See, Understand and Summarize it
Petros Koutras, Petros Maragos
In this work we propose a multi-task spatio-temporal network, called SUSiNet, that can jointly tackle the spatio-temporal problems of saliency estimation, action recognition and vi…
A Deep Learning Approach for Multi-View Engagement Estimation of Children in a Child-Robot Joint Attention task
Jack Hadfield, Georgia Chalvatzaki, Petros Koutras +3
In this work we tackle the problem of child engagement estimation while children freely interact with a robot in their room. We propose a deep-based multi-view solution that takes…
LSTM-based Network for Human Gait Stability Prediction in an Intelligent Robotic Rollator
Georgia Chalvatzaki, Petros Koutras, Jack Hadfield +3
In this work, we present a novel framework for on-line human gait stability prediction of the elderly users of an intelligent robotic rollator using Long Short Term Memory (LSTM) n…
Improved Frequency Modulation Features for Multichannel Distant Speech Recognition
Isidoros Rodomagoulakis, Petros Maragos
Frequency modulation features capture the fine structure of speech formants that constitute beneficial and supplementary to the traditional energy-based cepstral features. Improvem…
An Adaptive Pruning Algorithm for Spoofing Localisation Based on Tropical Geometry
Emmanouil Theodosis, Petros Maragos
The problem of spoofing attacks is increasingly relevant as digital systems are becoming more ubiquitous. Thus the detection of such attacks and the localisation of attackers have…
Tropical Modeling of Weighted Transducer Algorithms on Graphs
Emmanouil Theodosis, Petros Maragos
Weighted Finite State Transducers (WFSTs) are versatile data structures that can model a great number of problems, ranging from Automatic Speech Recognition to DNA sequencing. Trad…
A Tropical Approach to Neural Networks with Piecewise Linear Activations
Vasileios Charisopoulos, Petros Maragos
We present a new, unifying approach following some recent developments on the complexity of neural networks with piecewise linear activations. We treat neural network layers with p…
Sparsity in Max-Plus Algebra and Systems
Anastasios Tsiamis, Petros Maragos
We study sparsity in the max-plus algebraic setting. We seek both exact and approximate solutions of the max-plus linear equation with minimum cardinality of support. In the former…