2020 |
Maragos, P; Theodosis, E Tropical Geometry and Piecewise-Linear Approximation of Curves and Surfaces on Weighted Lattices Book Chapter Forthcoming M. Breuss A. Bruckstein, Kiselman C; Maragos, P (Ed.): Shape Analysis: Euclidean, Discrete and Algebraic Geometric Methods, Springer, Forthcoming. BibTeX | Tags: @inbook{Maragos2020, title = {Tropical Geometry and Piecewise-Linear Approximation of Curves and Surfaces on Weighted Lattices}, author = {P. Maragos and E. Theodosis}, editor = {M. Breuss, A. Bruckstein, C. Kiselman and P. Maragos}, booktitle = {Shape Analysis: Euclidean, Discrete and Algebraic Geometric Methods}, publisher = {Springer}, }
|
Tassopoulou, V; G. Retsinas, ; Maragos, P Enhancing Handwritten Text Recognition with N-gram sequence decomposition and Multitask Learning Conference Intl' Conference Pattern Recognition (ICPR 2020), Milan, Italy, 2020. BibTeX | Tags: | Links:  @conference{Tassopoulou2020, title = {Enhancing Handwritten Text Recognition with N-gram sequence decomposition and Multitask Learning}, author = {V. Tassopoulou and G. Retsinas, and P. Maragos}, booktitle = {Intl' Conference Pattern Recognition (ICPR 2020)}, }
|
Gkanatsios, Nikolaos; Pitsikalis, Vassilis; Maragos, Petros From Saturation to Zero-Shot Visual Relationship Detection Using Local Context Conference British Machine Vision Conference, Online, 2020. BibTeX | Tags: | Links:  @conference{Gkanatsios2020, title = {From Saturation to Zero-Shot Visual Relationship Detection Using Local Context}, author = {Nikolaos Gkanatsios and Vassilis Pitsikalis and Petros Maragos}, booktitle = { British Machine Vision Conference}, }
|
Chalvatzaki, Georgia; Koutras, Petros; Tsiami, Antigoni; Tzafestas, Costas S; Maragos, Petros i-Walk Intelligent Assessment System: Activity, Mobility, Intention, Communication Conference Proc. 16th European Computer Vision Conference Workshops (ECCVW) – 8th Int’l Workshop on Assistive Computer Vision and Robotics (ACVR-2020), Online, 2020. BibTeX | Tags: | Links:  @conference{Chalvatzaki2020, title = {i-Walk Intelligent Assessment System: Activity, Mobility, Intention, Communication}, author = {Georgia Chalvatzaki and Petros Koutras and Antigoni Tsiami and Costas S. Tzafestas and Petros Maragos}, booktitle = {Proc. 16th European Computer Vision Conference Workshops (ECCVW) – 8th Int’l Workshop on Assistive Computer Vision and Robotics (ACVR-2020)}, }
|
Filntisis, P P; Efthymiou, N; Potamianos, G; Maragos, P Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss Workshop Proc. 16th European Computer Vision Conference Workshops (ECCVW) - Workshop on Bodily Expressed Emotion Understanding, 2020. BibTeX | Tags: | Links:  @workshop{Filntisis2020, title = {Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss}, author = {P. P. Filntisis and N. Efthymiou and G. Potamianos and P. Maragos}, booktitle = {Proc. 16th European Computer Vision Conference Workshops (ECCVW) - Workshop on Bodily Expressed Emotion Understanding}, }
|
Werner, Christian; Dometios, Athanasios C; Tzafestas, Costas S; Maragos, Petros; Bauer, Jürgen M; Hauer, Klaus Evaluating the task effectiveness and user satisfaction with different operation modes of an assistive bathing robot in older adults Journal Article Assistive Technology, 0 , 2020, (PMID: 32286163). BibTeX | Tags: | Links:   @article{doi:10.1080/10400435.2020.1755744, title = {Evaluating the task effectiveness and user satisfaction with different operation modes of an assistive bathing robot in older adults}, author = {Christian Werner and Athanasios C Dometios and Costas S Tzafestas and Petros Maragos and Jürgen M Bauer and Klaus Hauer}, journal = {Assistive Technology}, volume = {0}, publisher = {Taylor & Francis}, note = {PMID: 32286163}, }
|
Smyrnis, Georgios; Maragos, Petros Multiclass Neural Network Minimization via Tropical Newton Polytope Approximation Conference International Conference on Machine Learning (ICML), Online, 2020. BibTeX | Tags: | Links:  @conference{Smyrnis2020, title = {Multiclass Neural Network Minimization via Tropical Newton Polytope Approximation}, author = {Georgios Smyrnis and Petros Maragos}, booktitle = {International Conference on Machine Learning (ICML)}, }
|
I. Maglogiannis A. Zlatintsi, Menychtas Papadimatos Filntisis Efthymiou Retsinas Tsanakas A D P P N G P; Maragos, P An intelligent cloud-based platform for effective monitoring of patients with psychotic disorders Conference Int’l Conf. on Artificial Intelligence Applications and Innovation (AIAI-2020), Halkidiki, Greece, 2020. BibTeX | Tags: | Links:  @conference{Maglogiannis2020, title = {An intelligent cloud-based platform for effective monitoring of patients with psychotic disorders}, author = {I. Maglogiannis, A. Zlatintsi, A. Menychtas, D. Papadimatos, P.P. Filntisis, N. Efthymiou, G. Retsinas, P. Tsanakas, and P. Maragos}, booktitle = {Int’l Conf. on Artificial Intelligence Applications and Innovation (AIAI-2020)}, }
|
Tsiami, A; Koutras, P; Maragos, P STAViS: Spatio-Temporal AudioVisual Saliency Network Conference IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, USA, 2020. BibTeX | Tags: @conference{Tsiami2020, title = {STAViS: Spatio-Temporal AudioVisual Saliency Network}, author = {A. Tsiami and P. Koutras and P. Maragos}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, }
|
G. Potamianos K. Papadimitriou, Efthimiou Fotinea Sapountzaki E S-E G; Maragos, P SL-ReDu: Greek Sign Language Recognition for Educational Applications. Project Description and Early Results Conference PETRA '20: Proceedings of the 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments, Corfu, Greece, 2020. BibTeX | Tags: | Links:  @conference{Potamianos2020, title = {SL-ReDu: Greek Sign Language Recognition for Educational Applications. Project Description and Early Results}, author = {G. Potamianos, K. Papadimitriou, E. Efthimiou, S-E Fotinea, G. Sapountzaki and P. Maragos}, booktitle = {PETRA '20: Proceedings of the 13th ACM International Conference on PErvasive Technologies Related to Assistive Environments}, }
|
Maragos, P; Theodosis, E Multivariate Tropical Regression and Piecewise-Linear Surface Fitting Conference ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020. BibTeX | Tags: | Links:  @conference{9054058, title = {Multivariate Tropical Regression and Piecewise-Linear Surface Fitting}, author = {P Maragos and E Theodosis}, booktitle = {ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {3822-3826}, }
|
Garoufis, C; Zlatintsi, A; Maragos, P An LSTM-Based Dynamic Chord Progression Generation System for Interactive Music Performance Conference ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020. BibTeX | Tags: @conference{9053992, title = {An LSTM-Based Dynamic Chord Progression Generation System for Interactive Music Performance}, author = {C Garoufis and A Zlatintsi and P Maragos}, booktitle = {ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {4502-4506}, }
|
Retsinas, G; Filntisis, P P; Efthymiou, N; Theodosis, E; Zlatintsi, A; Maragos, P Person Identification Using Deep Convolutional Neural Networks on Short-Term Signals from Wearable Sensors Conference ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020. BibTeX | Tags: | Links:  @conference{9053910, title = {Person Identification Using Deep Convolutional Neural Networks on Short-Term Signals from Wearable Sensors}, author = {G Retsinas and P P Filntisis and N Efthymiou and E Theodosis and A Zlatintsi and P Maragos}, booktitle = {ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {3657-3661}, }
|
Smyrnis, G; Maragos, P; Retsinas, G Maxpolynomial Division with Application To Neural Network Simplification Conference ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020. BibTeX | Tags: | Links:  @conference{9053540, title = {Maxpolynomial Division with Application To Neural Network Simplification}, author = {G Smyrnis and P Maragos and G Retsinas}, booktitle = {ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, pages = {4192-4196}, }
|
Zlatintsi, A; Dometios, A C; Kardaris, N; Rodomagoulakis, I; Koutras, P; Papageorgiou, X; Maragos, P; Tzafestas, C S; Vartholomeos, P; Hauer, K; Werner, C; Annicchiarico, R; Lombardi, M G; Adriano, F; Asfour, T; Sabatini, A M; Laschi, C; Cianchetti, M; Güler, A; Kokkinos, I; Klein, B; López, R I-Support: A robotic platform of an assistive bathing robot for the elderly population Journal Article Robotics and Autonomous Systems, 126 , pp. 103451, 2020, ISSN: 0921-8890. Abstract | BibTeX | Tags: Assistive human–robot interaction (HRI), Audio–gestural command recognition, Bathing robot, Human–robot communication, Multimodal dataset, Online validation with elderly users | Links:   @article{ZLATINTSI2020103451, title = {I-Support: A robotic platform of an assistive bathing robot for the elderly population}, author = {A Zlatintsi and A C Dometios and N Kardaris and I Rodomagoulakis and P Koutras and X Papageorgiou and P Maragos and C S Tzafestas and P Vartholomeos and K Hauer and C Werner and R Annicchiarico and M G Lombardi and F Adriano and T Asfour and A M Sabatini and C Laschi and M Cianchetti and A Güler and I Kokkinos and B Klein and R López}, journal = {Robotics and Autonomous Systems}, volume = {126}, pages = {103451}, }
In this paper we present a prototype integrated robotic system, the I-Support bathing robot, that aims at supporting new aspects of assisted daily-living activities on a real-life scenario. The paper focuses on describing and evaluating key novel technological features of the system, with the emphasis on cognitive human–robot interaction modules and their evaluation through a series of clinical validation studies. The I-Support project on its whole has envisioned the development of an innovative, modular, ICT-supported service robotic system that assists frail seniors to safely and independently complete an entire sequence of physically and cognitively demanding bathing tasks, such as properly washing their back and their lower limbs. A variety of innovative technologies have been researched and a set of advanced modules of sensing, cognition, actuation and control have been developed and seamlessly integrated to enable the system to adapt to the target population abilities. These technologies include: human activity monitoring and recognition, adaptation of a motorized chair for safe transfer of the elderly in and out the bathing cabin, a context awareness system that provides full environmental awareness, as well as a prototype soft robotic arm and a set of user-adaptive robot motion planning and control algorithms. This paper focuses in particular on the multimodal action recognition system, developed to monitor, analyze and predict user actions with a high level of accuracy and detail in real-time, which are then interpreted as robotic tasks. In the same framework, the analysis of human actions that have become available through the project’s multimodal audio–gestural dataset, has led to the successful modeling of Human–Robot Communication, achieving an effective and natural interaction between users and the assistive robotic platform. In order to evaluate the I-Support system, two multinational validation studies were conducted under realistic operating conditions in two clinical pilot sites. Some of the findings of these studies are presented and analyzed in the paper, showing good results in terms of: (i) high acceptability regarding the system usability by this particularly challenging target group, the elderly end-users, and (ii) overall task effectiveness of the system in different operating modes. |
Werner, Christian; Kardaris, Nikos; Koutras, Petros; Zlatintsi, Athanasia; Maragos, Petros; Bauer, Jürgen M; Hauer, Klaus Improving gesture-based interaction between an assistive bathing robot and older adults via user training on the gestural commands Journal Article Archives of Gerontology and Geriatrics, 87 , pp. 103996, 2020, ISSN: 0167-4943. Abstract | BibTeX | Tags: Activities of daily living, aged, Gestures, Human-robot interaction, Robotics, training | Links:   @article{WERNER2020103996, title = {Improving gesture-based interaction between an assistive bathing robot and older adults via user training on the gestural commands}, author = {Christian Werner and Nikos Kardaris and Petros Koutras and Athanasia Zlatintsi and Petros Maragos and Jürgen M Bauer and Klaus Hauer}, journal = {Archives of Gerontology and Geriatrics}, volume = {87}, pages = {103996}, }
Background Gesture-based human-robot interaction (HRI) depends on the technical performance of the robot-integrated gesture recognition system (GRS) and on the gestural performance of the robot user, which has been shown to be rather low in older adults. Training of gestural commands (GCs) might improve the quality of older users’ input for gesture-based HRI, which in turn may lead to an overall improved HRI. Objective To evaluate the effects of a user training on gesture-based HRI between an assistive bathing robot and potential elderly robot users. Methods Twenty-five older adults with bathing disability participated in this quasi-experimental, single-group, pre-/post-test study and underwent a specific user training (10−15 min) on GCs for HRI with the assistive bathing robot. Outcomes measured before and after training included participants’ gestural performance assessed by a scoring method of an established test of gesture production (TULIA) and sensor-based gestural performance (SGP) scores derived from the GRS-recorded data, and robot’s command recognition rate (CRR). Results Gestural performance (TULIA = +57.1 ± 56.2 %, SGP scores = +41.1 ± 74.4 %) and CRR (+31.9 ± 51.2 %) significantly improved over training (p < .001). Improvements in gestural performance and CRR were highly associated with each other (r = 0.80–0.81, p < .001). Participants with lower initial gestural performance and higher gerontechnology anxiety benefited most from the training. Conclusions Our study highlights that training in gesture-based HRI with an assistive bathing robot is highly beneficial for the quality of older users’ GCs, leading to higher CRRs of the robot-integrated GRS, and thus to an overall improved HRI. |
2019 |
Chalvatzaki, Georgia; Papageorgiou, Xanthi S; Maragos, Petros; Tzafestas, Costas S Learn to adapt to human walking: A Model-based Reinforcement Learning Approach for a Robotic Assistant Rollator Journal Article IEEE Robotics and Automation Letters (with IROS option), 4 (4), pp. 3774–3781, 2019. BibTeX | Tags: | Links:  @article{chalvatzaki2019learn, title = {Learn to adapt to human walking: A Model-based Reinforcement Learning Approach for a Robotic Assistant Rollator}, author = {Georgia Chalvatzaki and Xanthi S Papageorgiou and Petros Maragos and Costas S Tzafestas}, journal = {IEEE Robotics and Automation Letters (with IROS option)}, volume = {4}, number = {4}, pages = {3774--3781}, publisher = {IEEE}, }
|
Chalvatzaki, Georgia; Papageorgiou, Xanthi S; Maragos, Petros; Tzafestas, Costas S Comparing the Impact of Robotic Rollator Control Schemes on Elderly Gait using on-line LRF-based Gait Analysis Conference Proc. Workshop on Mobile Robot Assistants for the Elderly (MoRobAE) in 2019 IEEE Int’l Conference on Robotics and Automation (ICRA), Montreal, Canada, 2019. BibTeX | Tags: | Links:  @conference{Chalvatzaki2019b, title = {Comparing the Impact of Robotic Rollator Control Schemes on Elderly Gait using on-line LRF-based Gait Analysis}, author = {Georgia Chalvatzaki and Xanthi S. Papageorgiou and Petros Maragos and Costas S. Tzafestas}, booktitle = { Proc. Workshop on Mobile Robot Assistants for the Elderly (MoRobAE) in 2019 IEEE Int’l Conference on Robotics and Automation (ICRA)}, }
|
Filntisis, P P; Efthymiou, N; Koutras, P; Potamianos, G; Maragos, P Fusing Body Posture With Facial Expressions for Joint Recognition of Affect in Child–Robot Interaction Journal Article IEEE Robotics and Automation Letters (with IROS option), 4 (4), pp. 4011-4018, 2019. Abstract | BibTeX | Tags: Emotion recognition;Face recognition;Face;Robots;Databases;Training;Visualization;Gesture;posture and facial expressions;computer vision for other robotic applications;social human-robot interaction;deep learning in robotics and automation | Links:   @article{8769871, title = {Fusing Body Posture With Facial Expressions for Joint Recognition of Affect in Child–Robot Interaction}, author = {P P Filntisis and N Efthymiou and P Koutras and G Potamianos and P Maragos}, journal = {IEEE Robotics and Automation Letters (with IROS option)}, volume = {4}, number = {4}, pages = {4011-4018}, }
In this letter, we address the problem of multi-cue affect recognition in challenging scenarios such as child–robot interaction. Toward 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 GEneva multimodal emotion portrayal public database of acted emotions by adults, and show that the proposed method achieves significantly better results than facial-only expression baselines. |
Networks, RecNets: Channel-wise Recurrent Convolutional Neural RecNets: Channel-wise Recurrent Convolutional Neural Networks Conference Proceedings of the British Machine Vision Conference (BMVC), Cardiff, 2019. BibTeX | Tags: | Links:  @conference{Networks2019, title = {RecNets: Channel-wise Recurrent Convolutional Neural Networks}, author = {RecNets: Channel-wise Recurrent Convolutional Neural Networks}, booktitle = {Proceedings of the British Machine Vision Conference (BMVC)}, journal = {Proceedings of the British Machine Vision Conference (BMVC),}, }
|
Chalvatzaki, Georgia; Koutras, Petros; Hadfield, Jack; Papageorgiou, Xanthi S; Tzafestas, Costas S; Maragos, Petros On-line Human Gait Stability Prediction using LSTMs for the fusion of Deep-based Pose Estimation and LRF-based Augmented Gait State Estimation in an Intelligent Robotic Rollator Conference IEEE International Conference on Robotics & Automation (ICRA), Montreal, Canada, 2019. BibTeX | Tags: @conference{Chalvatzaki2019d, title = {On-line Human Gait Stability Prediction using LSTMs for the fusion of Deep-based Pose Estimation and LRF-based Augmented Gait State Estimation in an Intelligent Robotic Rollator}, author = {Georgia Chalvatzaki and Petros Koutras and Jack Hadfield and Xanthi S. Papageorgiou and Costas S. Tzafestas and Petros Maragos}, booktitle = {IEEE International Conference on Robotics & Automation (ICRA)}, }
|
Garoufis, C; Zlatintsi, A; Kritsis, K; Filntisis, P P; Katsouros, V; and Maragos, P An Environment for Gestural Interaction with 3D Virual Musical Instruments as an Educational Tool Conference Proc. 27th European Conf.(EUSIPCO-19), A Coruna, Spain, 2019. BibTeX | Tags: | Links:  @conference{Garoufis2019, title = {An Environment for Gestural Interaction with 3D Virual Musical Instruments as an Educational Tool}, author = {C. Garoufis and A. Zlatintsi and K. Kritsis and P.P. Filntisis and V. Katsouros and and P. Maragos }, booktitle = {Proc. 27th European Conf.(EUSIPCO-19)}, }
|
Rodomagoulakis, I; Maragos, P Improved Frequency Modulation Features for Multichannel Distant Speech Recognition Journal Article IEEE Journal of Selected Topics in Signal Processing, 13 (4), pp. 841-849, 2019. Abstract | BibTeX | Tags: | Links:   @article{8744655, title = {Improved Frequency Modulation Features for Multichannel Distant Speech Recognition}, author = {I Rodomagoulakis and P Maragos}, journal = {IEEE Journal of Selected Topics in Signal Processing}, volume = {13}, number = {4}, pages = {841-849}, }
Frequency modulation features capture the fine structure of speech formants that constitute beneficial to the traditional energy-based cepstral features by carrying supplementary information. Improvements have been demonstrated mainly in Gaussian mixture model (GMM)-hidden Markov model (HMM) systems for small and large vocabulary tasks. Yet, they have limited applications in deep neural network (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 DSR tasks on reverberant and noisy environments, where recognition rates are far from human performance. |
Maragos, P Tropical Geometry, Mathematical Morphology and Weighted Lattices Conference Proc. 14th Int’l Symposium on Mathematical Morphology (ISMM-2019), Saarbruecken, Germany, 2019. BibTeX | Tags: | Links:  @conference{Maragos2019, title = {Tropical Geometry, Mathematical Morphology and Weighted Lattices}, author = {P. Maragos}, booktitle = {Proc. 14th Int’l Symposium on Mathematical Morphology (ISMM-2019)}, pages = {3–15}, }
|
Chalvatzaki, G; Koutras, P; Hadfield, J; Papageorgiou, X S; Tzafestas, C S; Maragos, P LSTM-based Network for Human Gait Stability Prediction in an Intelligent Robotic Rollator Conference Proc. 2019 IEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, 2019. BibTeX | Tags: | Links:  @conference{Chalvatzaki2019, title = {LSTM-based Network for Human Gait Stability Prediction in an Intelligent Robotic Rollator}, author = {G. Chalvatzaki and P. Koutras and J. Hadfield and X. S. Papageorgiou and C. S. Tzafestas and P. Maragos}, booktitle = {Proc. 2019 IEEE International Conference on Robotics and Automation (ICRA)}, }
|
Papageorgiou, Xanthi S; Chalvatzaki, Georgia; Efthimiou, Eleni; Fotinea, Stavroula-Evita; Karavasili, Alexandra; Tzafestas, Costas S; Maragos, Petros; Vacalopoulou, Anna; Goulas, Theodore User Centered HRI Design for an Intelligent Robotic Rollator Conference Proc. Workshop on Mobile Robot Assistants for the Elderly (MoRobAE) in 2019 IEEE Int’l Conference on Robotics and Automation (ICRA), Montreal, Canada, 2019. BibTeX | Tags: | Links:  @conference{papageorgiouuser, title = {User Centered HRI Design for an Intelligent Robotic Rollator}, author = {Xanthi S Papageorgiou and Georgia Chalvatzaki and Eleni Efthimiou and Stavroula-Evita Fotinea and Alexandra Karavasili and Costas S Tzafestas and Petros Maragos and Anna Vacalopoulou and Theodore Goulas}, booktitle = {Proc. Workshop on Mobile Robot Assistants for the Elderly (MoRobAE) in 2019 IEEE Int’l Conference on Robotics and Automation (ICRA)}, }
|
Theodosis, E; Maragos, P Tropical Modeling of Weighted Transducer Algorithms on Graphs Conference Proc. IEEE Int'l Conf. Acous., Speech, and Signal Processing (ICASSP), 2019, ISSN: 2379-190X. Abstract | BibTeX | Tags: Weighted Finite State Transducers;tropical algebra;tropical geometry | Links:   @conference{8683127, title = {Tropical Modeling of Weighted Transducer Algorithms on Graphs}, author = {E Theodosis and P Maragos}, booktitle = {Proc. IEEE Int'l Conf. Acous., Speech, and Signal Processing (ICASSP)}, pages = {8653-8657}, }
Weighted Finite State Transducers (WFSTs) are versatile graphical automata 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 automata in order to optimize their size, but also the run time 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 analyze aspects of their tropical geometry. |
Tsiami, Antigoni; Koutras, Petros; Katsamanis, Athanasios; Vatakis, Argiro; Maragos, Petros A behaviorally inspired fusion approach for computational audiovisual saliency modeling Journal Article Signal Processing: Image Communication, 76 , pp. 186 - 200, 2019. Abstract | BibTeX | Tags: | Links:    @article{TSIAMI2019186, title = {A behaviorally inspired fusion approach for computational audiovisual saliency modeling}, author = {Antigoni Tsiami and Petros Koutras and Athanasios Katsamanis and Argiro Vatakis and Petros Maragos}, journal = {Signal Processing: Image Communication}, volume = {76}, pages = {186 - 200}, }
Human attention is highly influenced by multi-modal combinations of perceived sensory information and especially audiovisual information. Although systematic behavioral experiments have provided evidence that human attention is multi-modal, most bottom-up computational attention models, namely saliency models for fixation prediction, focus on visual information, largely ignoring auditory input. In this work, we aim to bridge the gap between findings from neuroscience concerning audiovisual attention and the computational attention modeling, by creating a 2-D bottom-up audiovisual saliency model. We experiment with various fusion schemes for integrating state-of-the-art auditory and visual saliency models in a single audiovisual attention/saliency model based on behavioral findings, that we validate in two experimental levels: (1) using results from behavioral experiments aiming to reproduce the results in a mostly qualitative manner and to ensure that our modeling is in line with behavioral findings, and (2) using 6 different databases with audiovisual human eye-tracking data. For this last purpose, we have also collected eye-tracking data for two databases: ETMD, a movie database that contains highly edited videos (movie clips), and SumMe, a database that contains unstructured and unedited user videos. Experimental results indicate that our proposed audiovisual fusion schemes in most cases improve performance compared to visual-only models, without any prior knowledge of the video/audio content. Also, they can be generalized and applied to any auditory saliency model and any visual spatio-temporal saliency model. |
Giannoulis, Panagiotis; Potamianos, Gerasimos; Maragos, Petros Room-localized speech activity detection in multi-microphone smart homes Journal Article EURASIP Journal on Audio, Speech, and Music Processing, 2019 (1), pp. 15, 2019, ISSN: 1687-4722. Abstract | BibTeX | Tags: | Links:   @article{Giannoulis2019, title = {Room-localized speech activity detection in multi-microphone smart homes}, author = {Panagiotis Giannoulis and Gerasimos Potamianos and Petros Maragos}, journal = {EURASIP Journal on Audio, Speech, and Music Processing}, volume = {2019}, number = {1}, pages = {15}, }
Voice-enabled interaction systems in domestic environments have attracted significant interest recently, being the focus of smart home research projects and commercial voice assistant home devices. Within the multi-module pipelines of such systems, speech activity detection (SAD) constitutes a crucial component, providing input to their activation and speech recognition subsystems. In typical multi-room domestic environments, SAD may also convey spatial intelligence to the interaction, in addition to its traditional temporal segmentation output, by assigning speech activity at the room level. Such room-localized SAD can, for example, disambiguate user command referents, allow localized system feedback, and enable parallel voice interaction sessions by multiple subjects in different rooms. In this paper, we investigate a room-localized SAD system for smart homes equipped with multiple microphones distributed in multiple rooms, significantly extending our earlier work. The system employs a two-stage algorithm, incorporating a set of hand-crafted features specially designed to discriminate room-inside vs. room-outside speech at its second stage, refining SAD hypotheses obtained at its first stage by traditional statistical modeling and acoustic front-end processing. Both algorithmic stages exploit multi-microphone information, combining it at the signal, feature, or decision level. The proposed approach is extensively evaluated on both simulated and real data recorded in a multi-room, multi-microphone smart home, significantly outperforming alternative baselines. Further, it remains robust to reduced microphone setups, while also comparing favorably to deep learning-based alternatives. |
Koutras, Petros; Maragos, Petros SUSiNet: See, Understand and Summarize it Conference Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019. BibTeX | Tags: | Links:  @conference{koutras2019susinet, title = {SUSiNet: See, Understand and Summarize it}, author = {Petros Koutras and Petros Maragos}, booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops}, }
|
Gkanatsios, N; Pitsikalis, V; Koutras, P; Zlatintsi, A; Maragos, P Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection Conference 2019 IEEE International Conference on Image Processing (ICIP), 2019. BibTeX | Tags: @conference{8803106, title = {Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection}, author = {N Gkanatsios and V Pitsikalis and P Koutras and A Zlatintsi and P Maragos}, booktitle = {2019 IEEE International Conference on Image Processing (ICIP)}, pages = {1840-1844}, }
|
Maragos, Petros Tropical Geometry, Mathematical Morphology and Weighted Lattices Conference Mathematical Morphology and Its Applications to Signal and Image Processing, Springer International Publishing, Cham, 2019, ISBN: 978-3-030-20867-7. Abstract | BibTeX | Tags: @conference{10.1007/978-3-030-20867-7_1, title = {Tropical Geometry, Mathematical Morphology and Weighted Lattices}, author = {Petros Maragos}, editor = {Bernhard Burgeth and Andreas Kleefeld and Beno{^i}t Naegel and Nicolas Passat and Benjamin Perret}, booktitle = {Mathematical Morphology and Its Applications to Signal and Image Processing}, pages = {3--15}, publisher = {Springer International Publishing}, }
Mathematical Morphology and Tropical Geometry share the same max/min-plus scalar arithmetic and matrix algebra. In this paper we summarize their common ideas and algebraic structure, generalize and extend both of them using weighted lattices and a max-$$backslashstar $$⋆algebra with an arbitrary binary operation $$backslashstar $$⋆that distributes over max, and outline applications to geometry, image analysis, and optimization. Further, we outline the optimal solution of max-$$backslashstar $$⋆equations using weighted lattice adjunctions, and apply it to optimal regression for fitting max-$$backslashstar $$⋆tropical curves on arbitrary data. |
Retsinas, George; Elafrou, Athena; Goumas, Georgios; Maragos, Petros RecNets: Channel-wise Recurrent Convolutional Neural Networks Conference British Machine Vision Conference (BMVC-2019), Cardiff, UK, 2019. BibTeX | Tags: @conference{retsinas2019recnets, title = {RecNets: Channel-wise Recurrent Convolutional Neural Networks}, author = {George Retsinas and Athena Elafrou and Georgios Goumas and Petros Maragos}, booktitle = {British Machine Vision Conference (BMVC-2019)}, }
|
Hadfield, Jack; Chalvatzaki, Georgia; Koutras, Petros; Khamassi, Mehdi; Tzafestas, Costas S; Maragos, Petros A Deep Learning Approach for Multi-View Engagement Estimation of Children in a Child-Robot Joint Attention Task Conference 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019), Macau, China, 2019. BibTeX | Tags: | Links:  @conference{hadfield:hal-02324118, title = {A Deep Learning Approach for Multi-View Engagement Estimation of Children in a Child-Robot Joint Attention Task}, author = {Jack Hadfield and Georgia Chalvatzaki and Petros Koutras and Mehdi Khamassi and Costas S Tzafestas and Petros Maragos}, booktitle = {2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019)}, }
|
Tsiamis, Anastasios; Maragos, Petros Sparsity in max-plus algebra and systems Journal Article Discrete Event Dynamic Systems, 29 (2), pp. 163–189, 2019. BibTeX | Tags: | Links:    @article{DBLP:journals/deds/TsiamisM19, title = {Sparsity in max-plus algebra and systems}, author = {Anastasios Tsiamis and Petros Maragos}, journal = {Discrete Event Dynamic Systems}, volume = {29}, number = {2}, pages = {163--189}, }
|
Maragos, Petros Tropical Geometry, Mathematical Morphology and Weighted Lattices Conference Mathematical Morphology and Its Applications to Signal and Image Processing
- 14th International Symposium, ISMM 2019, Saarbrücken, Germany,
July 8-10, 2019, Proceedings, 2019. BibTeX | Tags: | Links:   @conference{DBLP:conf/ismm/Maragos19, title = {Tropical Geometry, Mathematical Morphology and Weighted Lattices}, author = {Petros Maragos}, booktitle = {Mathematical Morphology and Its Applications to Signal and Image Processing - 14th International Symposium, ISMM 2019, Saarbrücken, Germany, July 8-10, 2019, Proceedings}, pages = {3--15}, }
|
2018 |
Efthymiou, N; Koutras, P; Filntisis, P ~P; Potamianos, G; Maragos, P MULTI-VIEW FUSION FOR ACTION RECOGNITION IN CHILD-ROBOT INTERACTION Conference Proc. IEEE Int'l Conf. on Image Processing, Athens, Greece, 2018. Abstract | BibTeX | Tags: action recognition, child-robot interaction, multi-view fusion | Links:  @conference{efthymiou18action, title = {MULTI-VIEW FUSION FOR ACTION RECOGNITION IN CHILD-ROBOT INTERACTION}, author = { N. Efthymiou and P. Koutras and P. ~P. Filntisis and G. Potamianos and P. Maragos}, booktitle = {Proc. IEEE Int'l Conf. on Image Processing}, }
Answering the challenge of leveraging computer vision methods in order to enhance Human Robot Interaction (HRI) experience, this work explores methods that can expand the capabilities of an action recognition system in such tasks. A multi-view action recognition system is proposed for integration in HRI scenarios with special users, such as children, in which there is limited data for training and many state-of-the-art techniques face difficulties. Different feature extraction approaches, encoding methods and fusion techniques are combined and tested in order to create an efficient system that recognizes children pantomime actions. This effort culminates in the integration of a robotic platform and is evaluated under an alluring Children Robot Interaction scenario. |
Hadfield, J; Koutras, P; Efthymiou, N; Potamianos, G; Tzafestas, C S; Maragos, P Object Assembly Guidance in Child-Robot Interaction using RGB-D based 3D Tracking Conference Proc. of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018), Madrid, Spain, 2018. BibTeX | Tags: @conference{Hadfield2018, title = {Object Assembly Guidance in Child-Robot Interaction using RGB-D based 3D Tracking}, author = {J. Hadfield and P. Koutras and N. Efthymiou and G. Potamianos and C.S. Tzafestas and P. Maragos}, booktitle = {Proc. of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)}, journal = {Proc. of 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)}, }
|
Zlatintsi, A; Filntisis, P P; Garoufis, C; Tsiami, A; Kritsis, K; Kaliakatsos-Papakostas, M A; Gkiokas, A; Katsouros, V; Maragos, P A Web-based Real-Time Kinect Application for Gestural Interaction with Virtual Musical Instruments Conference Proc. of Audio Mostly Conference (AM’18), Wrexham, North Wales, UK, 2018. BibTeX | Tags: | Links:  @conference{Zlatintsi2018, title = {A Web-based Real-Time Kinect Application for Gestural Interaction with Virtual Musical Instruments}, author = {A. Zlatintsi and P.P. Filntisis and C. Garoufis and A. Tsiami and K. Kritsis and M.A. Kaliakatsos-Papakostas and A. Gkiokas and V. Katsouros and P. Maragos}, booktitle = {Proc. of Audio Mostly Conference (AM’18)}, }
|
Chalvatzaki, G; Papageorgiou, X S; Tzafestas, C S; Maragos, P Augmented Human State Estimation Using Interacting Multiple Model Particle Filters With Probabilistic Data Association Journal Article IEEE Robotics and Automation Letters, 3 (3), pp. 1872-1879, 2018, ISSN: 2377-3766. BibTeX | Tags: | Links:   @article{8276229, title = {Augmented Human State Estimation Using Interacting Multiple Model Particle Filters With Probabilistic Data Association}, author = {G Chalvatzaki and X S Papageorgiou and C S Tzafestas and P Maragos}, journal = {IEEE Robotics and Automation Letters}, volume = {3}, number = {3}, pages = {1872-1879}, }
|
Dometios, A C; Zhou, Y; Papageorgiou, X S; Tzafestas, C S; Asfour, T Vision-Based Online Adaptation of Motion Primitives to Dynamic Surfaces: Application to an Interactive Robotic Wiping Task Journal Article IEEE Robotics and Automation Letters, 3 (3), pp. 1410-1417, 2018. Abstract | BibTeX | Tags: | Links:   @article{DZPTA18, title = {Vision-Based Online Adaptation of Motion Primitives to Dynamic Surfaces: Application to an Interactive Robotic Wiping Task}, author = {A C Dometios and Y Zhou and X S Papageorgiou and C S Tzafestas and T Asfour}, journal = {IEEE Robotics and Automation Letters}, volume = {3}, number = {3}, pages = {1410-1417}, }
Elderly or disabled people usually need augmented nursing attention both in home and clinical environments, especially to perform bathing activities. The development of an assistive robotic bath system, which constitutes a central motivation of this work, would increase the independence and safety of this procedure, ameliorating in this way the everyday life for this group of people. In general terms, the main goal of this work is to enable natural, physical human-robot interaction, involving human-friendly and user-adaptive on-line robot motion planning and interaction control. For this purpose, we employ imitation learning using a leader-follower framework called Coordinate Change Dynamic Movement Primitives (CC-DMP), in order to incorporate the expertise of professional carers for bathing sequences. In this letter, we propose a vision-based washing system, combining CC-DMP framework with a perception-based controller, to adapt the motion of robot’s end effector on moving and deformable surfaces, such as a human body part. The controller guarantees globally uniformly asymptotic convergence to the leader movement primitive while ensuring avoidance of restricted areas, such as sensitive skin body areas. We experimentally tested our approach on a setup including the humanoid robot ARMAR-III and a Kinect v2 camera. The robot executes motions learned from the publicly available KIT whole-body human motion database, achieving good tracking performance in challenging interactive task scenarios. |
Garoufis, C; Zlatintsi, A; Maragos, P A Collaborative System for Composing Music via Motion Using a Kinect Sensor and Skeletal Data Conference Proc. 15th International Sound & Music Computing Conference (SMC-2018), Limmesol, Cyprus, 2018. Abstract | BibTeX | Tags: @conference{Garoufis2018, title = {A Collaborative System for Composing Music via Motion Using a Kinect Sensor and Skeletal Data}, author = {C. Garoufis and A. Zlatintsi and P. Maragos}, booktitle = {Proc. 15th International Sound & Music Computing Conference (SMC-2018)}, }
This paper describes MoveSynth, a performance system for two players, who interact with it and collaborate with each other in various ways, including full-body movements, arm postures and continuous gestures, to compose music in real time. The system uses a Kinect sensor, in order to track the performers’ positions, as well as their arm and hand movements. In the system’s current state, the musical parameters that the performers can influence include the pitch and the volume of the music, the timbre of the sound, as well as the time interval between successive notes. We extensively experimented using various classifiers in order to detect the one that gives the optimal results regarding the task of continuous gesture and arm posture recognition, accomplishing 92.11% for continuous gestures and 99.33% for arm postures, using an 1-NN classifier with a condensed search space in both cases. Additionally, the qualitative results of the usability testing of the final system, which was performed by 9 users, are encouraging and identify possible avenues for further exploration and improvement. |
Theodosis, E; Maragos, P Analysis of the Viterbi Algorithm Using Tropical Algebra and Geometry Conference Proc. IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC-18), Kalamata, Greece,, 2018. BibTeX | Tags: | Links:  @conference{Theodosis2018, title = {Analysis of the Viterbi Algorithm Using Tropical Algebra and Geometry}, author = {E. Theodosis and P. Maragos}, booktitle = {Proc. IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC-18)}, }
|
Papageorgiou, X S; Chalvatzaki, G; Dometios, A; Tzafestas, C S Human-Centered Service Robotic Systems for Assisted Living Conference Proceedings of the 27th International Conference on Robotics in Alpe-Adria Danube Region (RAAD 2018), 2018. Abstract | BibTeX | Tags: | Links:  @conference{RAAD2018, title = {Human-Centered Service Robotic Systems for Assisted Living}, author = {X S Papageorgiou and G Chalvatzaki and A Dometios and C S Tzafestas}, booktitle = {Proceedings of the 27th International Conference on Robotics in Alpe-Adria Danube Region (RAAD 2018)}, }
Mobility impairment is a common problem for the elderly population which relates to difficulties in performing Activities of Daily Living (ADLs) and consequently leads to restrictions and the degradation of the living standards of the elders. When designing a user-friendly assistive device for mobility constrained people, the variable spectrum of disabilities is a factor that should affect the design process, since people with different impairments have different needs to be covered by the device, thus an adaptive behavior of those systems is necessary. Also, the performance of bathing activities includes several challenges for the elderly people, since such tasks require body flexibility. In this paper, we present current frameworks and solutions for intelligent robotic systems for assistive living involving human robot interaction in a natural interface. Our aim is to build such systems, in order to increase the independence and safety of these procedures. To achieve human - robot interaction in a natural way, we have to adapt the expertise of carers regarding bathing motions and walking assistance. The main goal of this work is to present recent research results towards the development of two real-life use cases incorporating intelligent robotic systems, aiming to support mobility and bathing activities for the elderly in order to provide context-aware and user-adaptive assistance. |
Bouritsas, G; Koutras, P; Zlatintsi, A; Maragos, Petros Multimodal Visual Concept Learning with Weakly Supervised Techniques Conference Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, Utah, USA, 2018. Abstract | BibTeX | Tags: | Links:  @conference{BKA+18, title = {Multimodal Visual Concept Learning with Weakly Supervised Techniques}, author = {G Bouritsas and P Koutras and A Zlatintsi and Petros Maragos}, booktitle = {Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, }
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. |
Tsiami, A; Koutras, P; Efthymiou, Niki; Filntisis, P P; Potamianos, G; Maragos, P Multi3: Multi-sensory Perception System for Multi-modal Child Interaction with Multiple Robots Conference IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, 2018. Abstract | BibTeX | Tags: | Links:  @conference{multi3, title = {Multi3: Multi-sensory Perception System for Multi-modal Child Interaction with Multiple Robots}, author = {A Tsiami and P Koutras and Niki Efthymiou and P P Filntisis and G Potamianos and P Maragos}, booktitle = {IEEE International Conference on Robotics and Automation (ICRA)}, }
Child-robot interaction is an interdisciplinary research area that has been attracting growing interest, primarily focusing on edutainment applications. A crucial factor to the successful deployment and wide adoption of such applications remains the robust perception of the child's multimodal actions, when interacting with the robot in a natural and untethered fashion. Since robotic sensory and perception capabilities are platform-dependent and most often rather limited, we propose a multiple Kinect-based system to perceive the child-robot interaction scene that is robot-independent and suitable for indoors interaction scenarios. The audio-visual input from the Kinect sensors is fed into speech, gesture, and action recognition modules, appropriately developed in this paper to address the challenging nature of child-robot interaction. For this purpose, data from multiple children are collected and used for module training or adaptation. Further, information from the multiple sensors is fused to enhance module performance. The perception system is integrated in a modular multi-robot architecture demonstrating its flexibility and scalability with different robotic platforms. The whole system, called Multi3, is evaluated, both objectively at the module level and subjectively in its entirety, under appropriate child-robot interaction scenarios containing several carefully designed games between children and robots. |
Zlatintsi, A; Rodomagoulakis, I; Koutras, P; Dometios, A ~C; Pitsikalis, V; Tzafestas, C ~S; Maragos, P Multimodal Signal Processing and Learning Aspects of Human-Robot Interaction for an Assistive Bathing Robot Conference Proc. IEEE Int'l Conf. Acous., Speech, and Signal Processing, Calgary, Canada, 2018. Abstract | BibTeX | Tags: Assistive HRI, Audio-gestural command recognition, Human-robot communication, Multimodal dataset, Online validation with elderly users | Links:  @conference{ZRK+18, title = {Multimodal Signal Processing and Learning Aspects of Human-Robot Interaction for an Assistive Bathing Robot}, author = {A Zlatintsi and I Rodomagoulakis and P Koutras and A ~C Dometios and V Pitsikalis and C ~S Tzafestas and P Maragos}, booktitle = {Proc. IEEE Int'l Conf. Acous., Speech, and Signal Processing}, }
We explore new aspects of assistive living on smart human-robot interaction (HRI) that involve automatic recognition and online validation of speech and gestures in a natural interface, providing social features for HRI. We introduce a whole framework and resources of a real-life scenario for elderly subjects supported by an assistive bathing robot, addressing health and hygiene care issues. We contribute a new dataset and a suite of tools used for data acquisition and a state-of-the-art pipeline for multimodal learning within the framework of the I-Support bathing robot, with emphasis on audio and RGB-D visual streams. We consider privacy issues by evaluating the depth visual stream along with the RGB, using Kinect sensors. The audio-gestural recognition task on this new dataset yields up to 84.5%, while the online validation of the I-Support system on elderly users accomplishes up to 84% when the two modalities are fused together. The results are promising enough to support further research in the area of multimodal recognition for assistive social HRI, considering the difficulties of the specific task. |
Tsiami, A; Filntisis, P P; Efthymiou, N; Koutras, P; Potamianos, G; Maragos, P FAR-FIELD AUDIO-VISUAL SCENE PERCEPTION OF MULTI-PARTY HUMAN-ROBOT INTERACTION FOR CHILDREN AND ADULTS Conference Proc. IEEE Int'l Conf. Acous., Speech, and Signal Processing (ICASSP), Calgary, Canada, 2018. Abstract | BibTeX | Tags: Human-robot interaction;speaker localization;distant speech recognition;gesture recognition;adaptation;fusion | Links:  @conference{tsiamifar, title = {FAR-FIELD AUDIO-VISUAL SCENE PERCEPTION OF MULTI-PARTY HUMAN-ROBOT INTERACTION FOR CHILDREN AND ADULTS}, author = {A Tsiami and P P Filntisis and N Efthymiou and P Koutras and G Potamianos and P Maragos}, booktitle = {Proc. IEEE Int'l Conf. Acous., Speech, and Signal Processing (ICASSP)}, }
Human-robot interaction (HRI) is a research area of growing interest with a multitude of applications for both children and adult user groups, as, for example, in edutainment and social robotics. Crucial, however, to its wider adoption remains the robust perception of HRI scenes in natural, untethered, and multi-party interaction scenarios, across user groups. Towards this goal, we investigate three focal HRI perception modules operating on data from multiple audio-visual sensors that observe the HRI scene from the far-field, thus bypassing limitations and platform-dependency of contemporary robotic sensing. In particular, the developed modules fuse intra- and/or inter-modality data streams to perform: (i) audio-visual speaker localization; (ii) distant speech recognition; and (iii) visual recognition of hand-gestures. Emphasis is also placed on ensuring high speech and gesture recognition rates for both children and adults. Development and objective evaluation of the three modules is conducted on a corpus of both user groups, collected by our far-field multi-sensory setup, for an interaction scenario of a question-answering ``guess-the-object'' collaborative HRI game with a ``Furhat'' robot. In addition, evaluation of the game incorporating the three developed modules is reported. Our results demonstrate robust far-field audio-visual perception of the multi-party HRI scene. |
Hadfield, Jack; Koutras, Petros; Efthymiou, Niki; Potamianos, Gerasimos; Tzafestas, Costas S; Maragos, Petros Object assembly guidance in child-robot interaction using RGB-D based 3d tracking Inproceedings 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 347–354, IEEE 2018. BibTeX | Tags: | Links:  @inproceedings{hadfield2018object, title = {Object assembly guidance in child-robot interaction using RGB-D based 3d tracking}, author = {Jack Hadfield and Petros Koutras and Niki Efthymiou and Gerasimos Potamianos and Costas S Tzafestas and Petros Maragos}, booktitle = {2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, pages = {347--354}, }
|
Kordonis, Ioannis; Maragos, Petros; Papavassilopoulos, George P Stochastic stability in Max-Product and Max-Plus Systems with Markovian Jumps Journal Article Automatica, 92 , pp. 123–132, 2018, ISSN: 00051098. Abstract | BibTeX | Tags: Max-plus systems, nonlinear systems, Stochastic stability, Stochastic systems | Links:   @article{348, title = {Stochastic stability in Max-Product and Max-Plus Systems with Markovian Jumps}, author = {Ioannis Kordonis and Petros Maragos and George P Papavassilopoulos}, journal = {Automatica}, volume = {92}, pages = {123--132}, }
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. |