arXiv subjects

Petros Maragos

Publications and source records attributed to Petros Maragos.

At least 91 records · Page 5Linked to original sources

arXiv2019

Fusing Body Posture with Facial Expressions for Joint Recognition of Affect in Child-Robot Interaction

In this paper we address the problem of multi-cue affect recognition in challenging scenarios such as child-robot interaction. Towards this goal we propose a method for automatic recognition of affect that leverages body expressions alongside facial ones, as opposed to traditional methods that typically focus only on the latter. Our deep-learning based method uses hierarchical multi-label annotations and multi-stage losses, can be trained both jointly and separately, and offers us computational models for both individual modalities, as well as for the whole body emotion. We evaluate our method on a challenging child-robot interaction database of emotional expressions collected by us, as well as on the GEMEP public database of acted emotions by adults, and show that the proposed method achieves significantly better results than facial-only expression baselines.

cs.CV↗

arXiv2019

A linear method for camera pair self-calibration and multi-view reconstruction with geometrically verified correspondences

We examine 3D reconstruction of architectural scenes in unordered sets of uncalibrated images. We introduce a linear method to self-calibrate and find the metric reconstruction of a camera pair. We assume unknown and different focal lengths but otherwise known internal camera parameters and a known projective reconstruction of the camera pair. We recover two possible camera configurations in space and use the Cheirality condition, that all 3D scene points are in front of both cameras, to disambiguate the solution. We show in two Theorems, first that the two solutions are in mirror positions and then the relations between their viewing directions. Our new method performs on par (median rotation error $ΔR = 3.49^{\circ}$) with the standard approach of Kruppa equations ($ΔR = 3.77^{\circ}$) for self-calibration and 5-Point algorithm for calibrated metric reconstruction of a camera pair. We reject erroneous image correspondences by introducing a method to examine whether point correspondences appear in the same order along $x, y$ image axes in image pairs. We evaluate this method by its precision and recall and show that it improves the robustness of point matches in architectural and general scenes. Finally, we integrate all the introduced methods to a 3D reconstruction pipeline. We utilize the numerous camera pair metric recontructions using rotation-averaging algorithms and a novel method to average focal length estimates.

cs.CV↗

arXiv2019

Sparsity in Max-Plus Algebra and Systems

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 case, the sparsest solution problem is shown to be equivalent to the minimum set cover problem and, thus, NP-complete. In the latter one, the approximation is quantified by the $\ell_{1}$ residual error norm, which is shown to have supermodular properties under some convex constraints, called lateness constraints. Thus, greedy approximation algorithms of polynomial complexity can be employed for both problems with guaranteed bounds of approximation. We also study the sparse recovery problem and present conditions, under which, the sparsest exact solution solves it. Through multi-machine interactive processes, we describe how the present framework could be applied to two practical discrete event systems problems: resource optimization and structure-seeking system identification. We also show how sparsity is related to the pruning problem. Finally, we present a numerical example of the structure-seeking system identification problem and we study the performance of the greedy algorithm via simulations.

math.OC↗

arXiv2019

SUSiNet: See, Understand and Summarize it

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 video summarization. Our approach employs a single network that is jointly end-to-end trained for all tasks with multiple and diverse datasets related to the exploring tasks. The proposed network uses a unified architecture that includes global and task specific layer and produces multiple output types, i.e., saliency maps or classification labels, by employing the same video input. Moreover, one additional contribution is that the proposed network can be deeply supervised through an attention module that is related to human attention as it is expressed by eye-tracking data. From the extensive evaluation, on seven different datasets, we have observed that the multi-task network performs as well as the state-of-the-art single-task methods (or in some cases better), while it requires less computational budget than having one independent network per each task.

cs.CV↗

arXiv2019

LSTM-based Network for Human Gait Stability Prediction in an Intelligent Robotic Rollator

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) networks, fusing multimodal RGB-D and Laser Range Finder (LRF) data from non-wearable sensors. A Deep Learning (DL) based approach is used for the upper body pose estimation. The detected pose is used for estimating the body Center of Mass (CoM) using Unscented Kalman Filter (UKF). An Augmented Gait State Estimation framework exploits the LRF data to estimate the legs' positions and the respective gait phase. These estimates are the inputs of an encoder-decoder sequence to sequence model which predicts the gait stability state as Safe or Fall Risk walking. It is validated with data from real patients, by exploring different network architectures, hyperparameter settings and by comparing the proposed method with other baselines. The presented LSTM-based human gait stability predictor is shown to provide robust predictions of the human stability state, and thus has the potential to be integrated into a general user-adaptive control architecture as a fall-risk alarm.

cs.RO↗

arXiv2019

Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection

Detecting visual relationships, i.e. triplets, is a challenging Scene Understanding task approached in the past via linguistic priors or spatial information in a single feature branch. We introduce a new deeply supervised two-branch architecture, the Multimodal Attentional Translation Embeddings, where the visual features of each branch are driven by a multimodal attentional mechanism that exploits spatio-linguistic similarities in a low-dimensional space. We present a variety of experiments comparing against all related approaches in the literature, as well as by re-implementing and fine-tuning several of them. Results on the commonly employed VRD dataset [1] show that the proposed method clearly outperforms all others, while we also justify our claims both quantitatively and qualitatively.

cs.CV↗

arXiv2019

A Tropical Approach to Neural Networks with Piecewise Linear Activations

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 piecewise linear activations as tropical polynomials, which generalize polynomials in the so-called $(\max, +)$ or tropical algebra, with possibly real-valued exponents. Motivated by the discussion in (arXiv:1402.1869), this approach enables us to refine their upper bounds on linear regions of layers with ReLU or leaky ReLU activations to $\min\left\{ 2^m, \sum_{j=0}^n \binom{m}{j} \right\}$, where $n, m$ are the number of inputs and outputs, respectively. Additionally, we recover their upper bounds on maxout layers. Our work follows a novel path, exclusively under the lens of tropical geometry, which is independent of the improvements reported in (arXiv:1611.01491, arXiv:1711.02114). Finally, we present a geometric approach for effective counting of linear regions using random sampling in order to avoid the computational overhead of exact counting approaches

stat.ML↗

arXiv2018

Detecting Adversarial Examples in Convolutional Neural Networks

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 are vulnerable to certain inputs, the adversarial examples, which although are not easily perceived by humans, they can lead a neural network to produce faulty results. This paper focuses on the detection of adversarial examples, which are created for convolutional neural networks that perform image classification. We propose three methods for detecting possible adversarial examples and after we analyze and compare their performance, we combine their best aspects to develop an even more robust approach. The first proposed method is based on the regularization of the feature vector that the neural network produces as output. The second method detects adversarial examples by using histograms, which are created from the outputs of the hidden layers of the neural network. These histograms create a feature vector which is used as the input of an SVM classifier, which classifies the original input either as an adversarial or as a real input. Finally, for the third method we introduce the concept of the residual image, which contains information about the parts of the input pattern that are ignored by the neural network. This method aims at the detection of possible adversarial examples, by using the residual image and reinforcing the parts of the input pattern that are ignored by the neural network. Each one of these methods has some novelties and by combining them we can further improve the detection results. For the proposed methods and their combination, we present the results of detecting adversarial examples on the MNIST dataset. The combination of the proposed methods offers some improvements over similar state of the art approaches.

cs.CV↗

arXiv2018

A Deep Learning Approach for Multi-View Engagement Estimation of Children in a Child-Robot Joint Attention task

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 advantage of recent developments in human pose detection. We extract the child's pose from different RGB-D cameras placed elegantly in the room, fuse the results and feed them to a deep neural network trained for classifying engagement levels. The deep network contains a recurrent layer, in order to exploit the rich temporal information contained in the pose data. The resulting method outperforms a number of baseline classifiers, and provides a promising tool for better automatic understanding of a child's attitude, interest and attention while cooperating with a robot. The goal is to integrate this model in next generation social robots as an attention monitoring tool during various CRI tasks both for Typically Developed (TD) children and children affected by autism (ASD).

cs.RO↗

arXiv2018

Improved Frequency Modulation Features for Multichannel Distant Speech Recognition

Frequency modulation features capture the fine structure of speech formants that constitute beneficial and supplementary to the traditional energy-based cepstral features. Improvements have been demonstrated mainly in GMM-HMM systems for small and large vocabulary tasks. Yet, they have limited applications in DNN-HMM systems and Distant Speech Recognition (DSR) tasks. Herein, we elaborate on their integration within state-of-the-art front-end schemes that include post-processing of MFCCs resulting in discriminant and speaker adapted features of large temporal contexts. We explore 1) multichannel demodulation schemes for multi-microphone setups, 2) richer descriptors of frequency modulations, and 3) feature transformation and combination via hierarchical deep networks. We present results for tandem and hybrid recognition with GMM and DNN acoustic models, respectively. The improved modulation features are combined efficiently with MFCCs yielding modest and consistent improvements in multichannel distant speech recognition tasks on reverberant and noisy environments, where recognition rates are far from human performance.

cs.SD↗

arXiv2018

Tropical Modeling of Weighted Transducer Algorithms on Graphs

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. Traditional computer science algorithms are employed when working with these structures in order to optimise their size, but also the runtime of decoding algorithms. However, these algorithms are not unified under a common framework that would allow for their treatment as a whole. Moreover, the inherent geometrical representation of WFSTs, coupled with the topology-preserving algorithms that operate on them make the structures ideal for tropical analysis. The benefits of such analysis have a twofold nature; first, matrix operations offer a connection to nonlinear vector space and spectral theory, and, second, tropical algebra offers a connection to tropical geometry. In this work we model some of the most frequently used algorithms in WFSTs by using tropical algebra; this provides a theoretical unification and allows us to also analyse aspects of their tropical geometry. Further, we provide insights via numerical examples.

math.RA↗

arXiv2018

An Adaptive Pruning Algorithm for Spoofing Localisation Based on Tropical Geometry

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 been objects of recent study. After an attack has been detected, various algorithms have been proposed in order to localise the attacker. In this work we propose a new adaptive pruning algorithm inspired by the tropical and geometrical analysis of the traditional Viterbi pruning algorithm to solve the localisation problem. In particular, the proposed algorithm tries to localise the attacker by adapting the leniency parameter based on estimates about the state of the solution space. These estimates stem from the enclosed volume and the entropy of the solution space, as they were introduced in our previous works.

cs.CR↗

arXiv2018

Multimodal Visual Concept Learning with Weakly Supervised Techniques

Despite the availability of a huge amount of video data accompanied by descriptive texts, it is not always easy to exploit the information contained in natural language in order to automatically recognize video concepts. Towards this goal, in this paper we use textual cues as means of supervision, introducing two weakly supervised techniques that extend the Multiple Instance Learning (MIL) framework: the Fuzzy Sets Multiple Instance Learning (FSMIL) and the Probabilistic Labels Multiple Instance Learning (PLMIL). The former encodes the spatio-temporal imprecision of the linguistic descriptions with Fuzzy Sets, while the latter models different interpretations of each description's semantics with Probabilistic Labels, both formulated through a convex optimization algorithm. In addition, we provide a novel technique to extract weak labels in the presence of complex semantics, that consists of semantic similarity computations. We evaluate our methods on two distinct problems, namely face and action recognition, in the challenging and realistic setting of movies accompanied by their screenplays, contained in the COGNIMUSE database. We show that, on both tasks, our method considerably outperforms a state-of-the-art weakly supervised approach, as well as other baselines.

cs.CV↗

arXiv2018

Online Wideband Spectrum Sensing Using Sparsity

Wideband spectrum sensing is an essential part of cognitive radio systems. Exact spectrum estimation is usually inefficient as it requires sampling rates at or above the Nyquist rate. Using prior information on the structure of the signal could allow near exact reconstruction at much lower sampling rates. Sparsity of the sampled signal in the frequency domain is one of the popular priors studied for cognitive radio applications. Reconstruction of signals under sparsity assumptions has been studied rigorously by researchers in the field of Compressed Sensing (CS). CS algorithms that operate on batches of samples are known to be robust but can be computationally costly, making them unsuitable for cheap low power cognitive radio devices that require spectrum sensing in real time. On the other hand, on line algorithms that are based on variations of the Least Mean Squares (LMS) algorithm have very simple updates so they are computationally efficient and can easily adapt in real time to changes of the underlying spectrum. In this paper we will present two variations of the LMS algorithm that enforce sparsity in the estimated spectrum given an upper bound on the number of non-zero coefficients. Assuming that the number of non-zero elements in the spectrum is known we show that under conditions the hard threshold operation can only reduce the error of our estimation. We will also show that we can estimate the number of non-zero elements of the spectrum at each iteration based on our online estimations. Finally, we numerically compare our algorithm with other on line sparsity-inducing algorithms in the literature.

cs.IT↗

arXiv2017

Dynamical Systems On Weighted Lattices: General Theory

In this work a theory is developed for unifying large classes of nonlinear discrete-time dynamical systems obeying a superposition of a weighted maximum or minimum type. The state vectors and input-output signals evolve on nonlinear spaces which we call complete weighted lattices and include as special cases the nonlinear vector spaces of minimax algebra. Their algebraic structure has a polygonal geometry. Some of the special cases unified include max-plus, max-product, and probabilistic dynamical systems. We study problems of representation in state and input-output spaces using lattice monotone operators, state and output responses using nonlinear convolutions, solving nonlinear matrix equations using lattice adjunctions, stability and controllability. We outline applications in state-space modeling of nonlinear filtering; dynamic programming (Viterbi algorithm) and shortest paths (distance maps); fuzzy Markov chains; and tracking audio-visual salient events in multimodal information streams using generalized hidden Markov models with control inputs.

eess.SY↗

arXiv2017

Stochastic Stability in Max-Product and Max-Plus Systems with Markovian Jumps

We study Max-Product and Max-Plus Systems with Markovian Jumps and focus on stochastic stability problems. At first, a Lyapunov function is derived for the asymptotically stable deterministic Max-Product Systems. This Lyapunov function is then adjusted to derive sufficient conditions for the stochastic stability of Max-Product systems with Markovian Jumps. Many step Lyapunov functions are then used to derive necessary and sufficient conditions for stochastic stability. The results for the Max-Product systems are then applied to Max-Plus systems with Markovian Jumps, using an isomorphism and almost sure bounds for the asymptotic behavior of the state are obtained. A numerical example illustrating the application of the stability results on a production system is also given.

eess.SY↗

arXiv2017

A Finite Element Computational Framework for Active Contours on Graphs

In this paper we present a new framework for the solution of active contour models on graphs. With the use of the Finite Element Method we generalize active contour models on graphs and reduce the problem from a partial differential equation to the solution of a sparse non-linear system. Additionally, we extend the proposed framework to solve models where the curve evolution is locally constrained around its current location. Based on the previous extension, we propose a fast algorithm for the solution of a wide range active contour models. Last, we present a supervised extension of Geodesic Active Contours for image segmentation and provide experimental evidence for the effectiveness of our framework.

cs.CV↗

arXiv2016

Theoretical Analysis of Active Contours on Graphs

Active contour models based on partial differential equations have proved successful in image segmentation, yet the study of their geometric formulation on arbitrary geometric graphs is still at an early stage. In this paper, we introduce geometric approximations of gradient and curvature, which are used in the geodesic active contour model. We prove convergence in probability of our gradient approximation to the true gradient value and derive an asymptotic upper bound for the error of this approximation for the class of random geometric graphs. Two different approaches for the approximation of curvature are presented and both are also proved to converge in probability in the case of random geometric graphs. We propose neighborhood-based filtering on graphs to improve the accuracy of the aforementioned approximations and define two variants of Gaussian smoothing on graphs which include normalization in order to adapt to graph non-uniformities. The performance of our active contour framework on graphs is demonstrated in the segmentation of regular images and geographical data defined on arbitrary graphs.

cs.CV↗