2026
|
D. N. Makropoulos, C. Garoufis, A. Tsiami, P. P. Filntisis, P. Maragos Representation-Diverse Self-Supervision for Cross-Domain Bioacoustic Learning in Low-Resource Settings Conference Proc. IEEE Int’l Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026), Barcelona, Spain, 2026. BibTeX | Links: [PDF] @conference{Makropoulos2026,
title = {Representation-Diverse Self-Supervision for Cross-Domain Bioacoustic Learning in Low-Resource Settings},
author = {D. N. Makropoulos, C. Garoufis, A. Tsiami, P. P. Filntisis, P. Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Makropoulos_Representation-Diverse_SelfSupervision_for_CrossDomain_Bioacoustic_Learning_in_Low-Resource_Settings_ICASSP26.pdf},
doi = {10.1109/ICASSP55912.2026.11461507},
year = {2026},
date = {2026-05-04},
booktitle = {Proc. IEEE Int’l Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026)},
pages = {15227-15231},
address = {Barcelona, Spain},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2025
|
Garyfalli V, Kalisperakis E, Smyrnis A, Lazaridi M, Karantinos T, Mantas A, Filntisis P P, Efthymiou N, Zlatintsi A, Maragos P, N Smyrnis Smartwatch-Derived Digital Phenotypes Relate to Psychopathology Dimensions in Patients With Psychotic Spectrum Disorders: Longitudinal Observational Study Journal Article JMIR Ment Health, 12 , pp. e75774, 2025. BibTeX | Links: [PDF] @article{V2025,
title = {Smartwatch-Derived Digital Phenotypes Relate to Psychopathology Dimensions in Patients With Psychotic Spectrum Disorders: Longitudinal Observational Study},
author = {Garyfalli V and Kalisperakis E and Smyrnis A and Lazaridi M and Karantinos T and Mantas A and Filntisis P P and Efthymiou N and Zlatintsi A and Maragos P and N Smyrnis},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_Garyfalli_Smartch-DerivedDigitalPhenotypesRelateToPsychopathodogy_JMIR-1.pdf},
doi = {10.2196/75774},
year = {2025},
date = {2025-04-01},
journal = {JMIR Ment Health},
volume = {12},
pages = {e75774},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
B. Psomas, G. Retsinas, N. Efthymiadis, P. Filntisis, Y. Avrithis, P. Maragos, O. Chum, G. Tolias Instance-Level Composed Image Retrieval Conference Proc. Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, USA, 2025. BibTeX | Links: [Webpage] [PDF] @conference{Psomas2025,
title = {Instance-Level Composed Image Retrieval},
author = {B. Psomas, G. Retsinas, N. Efthymiadis, P. Filntisis, Y. Avrithis, P. Maragos, O. Chum, G. Tolias},
url = {https://openreview.net/forum?id=7NEP4jGKwA
http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_PsomasRetsinasEtAl_Instance-Level-Composed-Image-Retrieval_NeurIPS.pdf},
year = {2025},
date = {2025-12-02},
booktitle = {Proc. Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025)},
address = {San Diego, USA},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
T. Aravanis, P. P. Filntisis, P. Maragos, G. Retsinas Only-Style: Stylistic Consistency in Image Generation without Content Leakage Conference Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, Honolulu, Hawaii, 2025. BibTeX | Links: [PDF] @conference{Aravanis2025,
title = {Only-Style: Stylistic Consistency in Image Generation without Content Leakage},
author = {T. Aravanis, P. P. Filntisis, P. Maragos, G. Retsinas},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_Aravanis_Only-Style_Stylistic_Consistency_in_Image_Generation_without_Content_Leakage_ICCVW.pdf},
year = {2025},
date = {2025-10-19},
booktitle = {Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
address = {Honolulu, Hawaii},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
K. Papadimitriou, P. Filntisis, G. Retsinas, G. Potamianos, P. Maragos Seeing in 2D, Thinking in 3D: 3D Hand Mesh-Guided Feature Learning for Continuous Fingerspelling Conference Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, Honolulu, Hawaii, 2025. BibTeX | Links: [PDF] @conference{Papadimitriou2025,
title = {Seeing in 2D, Thinking in 3D: 3D Hand Mesh-Guided Feature Learning for Continuous Fingerspelling},
author = {K. Papadimitriou, P. Filntisis, G. Retsinas, G. Potamianos, P. Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_Papadimitriou_Seeing_in_2D_Thinking_in_3D_ICCVW.pdf},
year = {2025},
date = {2025-10-19},
booktitle = {Proc. IEEE/CVF International Conference on Computer Vision (ICCV) Workshops},
address = {Honolulu, Hawaii},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
M. Glytsos, P. P. Filntisis, G. Retsinas, P. Maragos Category-Level 6D Object Pose Estimation in Agricultural Settings Using a Lattice-Deformation Framework and Diffusion-Augmented Synthetic Data Conference Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 2025. BibTeX | Links: [PDF] @conference{Glytsos2025,
title = {Category-Level 6D Object Pose Estimation in Agricultural Settings Using a Lattice-Deformation Framework and Diffusion-Augmented Synthetic Data},
author = {M. Glytsos, P. P. Filntisis, G. Retsinas, P. Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_Glytsos_6D-Object-PoseEstimation-in-Agriculture_LatticeDeform-DiffusionAugment-SyntheticData_IROS.pdf},
year = {2025},
date = {2025-10-19},
booktitle = {Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
address = {Hangzhou, China},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
N. Giannakakis, A. Manetas, P. P. Filntisis, P. Maragos, G. Retsinas Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning Conference Proc. 2025 IEEE Int'l Conf. on Development and Learning (ICDL), Prague, Czechia, 2025. BibTeX | Links: [PDF] @conference{Giannakakis2025,
title = {Object-Centric Action-Enhanced Representations for Robot Visuo-Motor Policy Learning},
author = {N. Giannakakis and A. Manetas and P. P. Filntisis and P. Maragos and G. Retsinas},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_GiannakakisManetas_ObjectCentricActionRepresent-RobotVisuoMotorLearn_ICDL.pdf},
doi = {10.1109/ICDL63968.2025.11204392},
year = {2025},
date = {2025-09-16},
booktitle = {Proc. 2025 IEEE Int'l Conf. on Development and Learning (ICDL)},
address = {Prague, Czechia},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
C. Pratikaki, P. P. Filntisis, A. Katsamanis, A. Roussos, P. Maragos A Transformer-Based Framework for Greek Sign Language Production using Extended Skeletal Motion Representations Conference Proc. 18th ACM Int'l Conf. on PErvasive Technologies Related to Assistive Environments (PETRA 2025), Corfu, Greece, 2025. BibTeX | Links: [PDF] @conference{Pratikaki2025,
title = {A Transformer-Based Framework for Greek Sign Language Production using Extended Skeletal Motion Representations},
author = {C. Pratikaki and P. P. Filntisis and A. Katsamanis and A. Roussos and P. Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_Pratikaki_Transformer-for-Greek-Sign-Language-Production-using-Skeletal-Motion_PETRA.pdf},
year = {2025},
date = {2025-06-25},
booktitle = {Proc. 18th ACM Int'l Conf. on PErvasive Technologies Related to Assistive Environments (PETRA 2025)},
address = {Corfu, Greece},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
D. N. Makropoulos, P. P. Filntisis, A. Prospathopoulos, D. Kassis, A. Tsiami, P. Maragos Improving Classification of Marine Mammal Vocalizations Using Vision Transformers and Phase-Related Features Conference Proc. 25th Int'l Conf. on Digital Signal Processing (DSP 2025), Costa Navarino, Greece, 2025. BibTeX | Links: [PDF] @conference{Makropoulos2025,
title = {Improving Classification of Marine Mammal Vocalizations Using Vision Transformers and Phase-Related Features},
author = {D. N. Makropoulos and P. P. Filntisis and A. Prospathopoulos and D. Kassis and A. Tsiami and P. Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_Makropoulos_ClassificationMarineMammalVocalizations_DSP.pdf},
year = {2025},
date = {2025-06-25},
booktitle = {Proc. 25th Int'l Conf. on Digital Signal Processing (DSP 2025)},
address = {Costa Navarino, Greece},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
P. P. Filntisis, E. Tsaprazlis, P. Oikonomou, F. Mattioli, V. G. Santucci, G. Retsinas, P. Maragos Towards Open-ended Robotic Exploration using Vision-Inspired Similarity and Foundation Models Conference Proc. 2025 IEEE International Conference on Robotics and Automation (ICRA 2025), Atlanta, USA, 2025. BibTeX | Links: [PDF] @conference{Filntisis2025,
title = {Towards Open-ended Robotic Exploration using Vision-Inspired Similarity and Foundation Models},
author = {P. P. Filntisis and E. Tsaprazlis and P. Oikonomou and F. Mattioli and V. G. Santucci and G. Retsinas and P. Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2025_Filntisis_Open-endedRoboticExplorationUsingVision-InspiredSimilarity-Foundation-Models_ICRA.pdf},
year = {2025},
date = {2025-05-01},
booktitle = {Proc. 2025 IEEE International Conference on Robotics and Automation (ICRA 2025)},
address = {Atlanta, USA},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2024
|
A Zlatintsi, P P Filntisis, N Efthymiou, C Garoufis, G Retsinas, T Sounapoglou, I Maglogiannis, P Tsanakas, N Smyrnis, P Maragos Person Identification and Relapse Detection from Continuous Recordings of Biosignals Challenge: Overview and Results Journal Article IEEE Open Journal of Signal Processing, 2024. BibTeX | Links: [PDF] @article{zlatintsi2024person,
title = {Person Identification and Relapse Detection from Continuous Recordings of Biosignals Challenge: Overview and Results},
author = {A Zlatintsi and P P Filntisis and N Efthymiou and C Garoufis and G Retsinas and T Sounapoglou and I Maglogiannis and P Tsanakas and N Smyrnis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Zlatintsi_e-PreventionChallengeOverview_OJSP-2024_preprint.pdf},
doi = {10.1109/OJSP.2024.3376300},
year = {2024},
date = {2024-01-01},
journal = {IEEE Open Journal of Signal Processing},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
George Retsinas, Panagiotis P Filntisis, Radek Danecek, Victoria F Abrevaya, Anastasios Roussos, Timo Bolkart, Petros Maragos 3D Facial Expressions through Analysis-by-Neural-Synthesis Conference Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. BibTeX | Links: [PDF] @conference{Retsinas2024,
title = {3D Facial Expressions through Analysis-by-Neural-Synthesis},
author = {George Retsinas and Panagiotis P Filntisis and Radek Danecek and Victoria F Abrevaya and Anastasios Roussos and Timo Bolkart and Petros Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Retsinas_SMIRK-3D_Facial_Expressions_through_Analysis-by-Neural-Synthesis_CVPR2024.pdf},
year = {2024},
date = {2024-06-17},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages = {2490-2501},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
N Efthymiou, G Retsinas, P P Filntisis, P Maragos Augmenting Transformer Autoencoders with Phenotype Classification for Robust Detection of Psychotic Relapses Conference Proc. IEEE Int’l Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024), Seoul, Korea, 2024. BibTeX | Links: [PDF] @conference{Efthymiou2024,
title = {Augmenting Transformer Autoencoders with Phenotype Classification for Robust Detection of Psychotic Relapses},
author = {N Efthymiou and G Retsinas and P P Filntisis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Efthymiou_TransformerPhenotypeClassif-DetectPsychoticRelapses_ICASSP2024.pdf},
year = {2024},
date = {2024-04-01},
booktitle = {Proc. IEEE Int’l Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)},
address = {Seoul, Korea},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2023
|
E Kalisperakis, T Karantinos, M Lazaridi, V Garyfalli, P P Filntisis, A Zlatintsi, N Efthymiou, A Mantas, L Mantonakis, T Mougiakos, I Maglogiannis, P Tsanakas, P Maragos, N Smyrnis Smartwatch digital phenotypes predict positive and negative symptom variation in a longitudinal monitoring study of patients with psychotic disorders Journal Article Frontiers in Psychiatry, 14 , 2023. BibTeX | Links: [PDF] @article{kalisperakis2023smartwatch,
title = {Smartwatch digital phenotypes predict positive and negative symptom variation in a longitudinal monitoring study of patients with psychotic disorders},
author = {E Kalisperakis and T Karantinos and M Lazaridi and V Garyfalli and P P Filntisis and A Zlatintsi and N Efthymiou and A Mantas and L Mantonakis and T Mougiakos and I Maglogiannis and P Tsanakas and P Maragos and N Smyrnis},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2023_KalisperakisEtAl_ePrevention_FrontiersPsychiatry.pdf},
doi = {10.3389/fpsyt.2023.1024965},
year = {2023},
date = {2023-01-01},
journal = {Frontiers in Psychiatry},
volume = {14},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
N Kegkeroglou, P P Filntisis, P Maragos Medical Face Masks and Emotion Recognition from the Body: Insights from a Deep Learning Perspective Conference Proc. Int'l Conf. on Pervasive Technologies Related to Assistive Environments (PETRA 2023), 2023. BibTeX | Links: [PDF] @conference{Kegkeroglou2023,
title = {Medical Face Masks and Emotion Recognition from the Body: Insights from a Deep Learning Perspective},
author = {N Kegkeroglou and P P Filntisis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Kegkeroglou_MedicalFaceMasks-EmotionRecognFromBody_PETRA2023.pdf},
year = {2023},
date = {2023-07-01},
booktitle = {Proc. Int'l Conf. on Pervasive Technologies Related to Assistive Environments (PETRA 2023)},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
G Retsinas, G Sfikas, P P Filntisis, P Maragos Newton-based Trainable Learning Rate Conference Proc. 48th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023), Rhodes, Greece, 2023. BibTeX | Links: [PDF] @conference{retsinas2023newton,
title = {Newton-based Trainable Learning Rate},
author = {G Retsinas and G Sfikas and P P Filntisis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Retsinas_ICASSP2023_Newton-Based-Trainable-Learning-Rate.pdf},
year = {2023},
date = {2023-06-01},
booktitle = {Proc. 48th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)},
address = {Rhodes, Greece},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
E Fekas, A Zlatintsi, P P Filntisis, C Garoufis, N Efthymiou, P Maragos Relapse Prediction from Long-Term Wearable Data using Self-Supervised Learning and Survival Analysis Conference Proc. 48th Int'l Conf. on Acoustics, Speech, and Signal Processing (ICASSP-2023), Rhodes Island, 2023. BibTeX | Links: [PDF] [Slides] @conference{fekas2023relapse,
title = {Relapse Prediction from Long-Term Wearable Data using Self-Supervised Learning and Survival Analysis},
author = {E Fekas and A Zlatintsi and P P Filntisis and C Garoufis and N Efthymiou and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Fekas_ICASSP2023_paper.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Fekas_ICASSP2023_slides.pdf},
year = {2023},
date = {2023-06-01},
booktitle = {Proc. 48th Int'l Conf. on Acoustics, Speech, and Signal Processing (ICASSP-2023)},
address = {Rhodes Island},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
N Efthymiou, G Retsinas, P P Filntisis, A Zlatintsi, E Kalisperakis, V Garyfalli, T Karantinos, M Lazaridi, N Smyrnis, P Maragos From Digital Phenotype Identification To Detection Of Psychotic Relapses Conference Proc. IEEE International Conference on Healthcare Informatics, Houston, TX, USA, 2023. BibTeX | Links: [PDF] [Slides] @conference{efthymiou2023digital,
title = {From Digital Phenotype Identification To Detection Of Psychotic Relapses},
author = {N Efthymiou and G Retsinas and P P Filntisis and A Zlatintsi and E Kalisperakis and V Garyfalli and T Karantinos and M Lazaridi and N Smyrnis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Efthymiou_ICHI2023_paper.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Efthymiou_ICHI2023_slides.pdf},
year = {2023},
date = {2023-06-01},
booktitle = {Proc. IEEE International Conference on Healthcare Informatics},
address = {Houston, TX, USA},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
D Anagnostopoulou, G Retsinas, N Efthymiou, P P Filntisis, P Maragos A Realistic Synthetic Mushroom Scenes Dataset Conference Proc. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4th Agriculture Vision Workshop, Vancouver, Canada, 2023. BibTeX | Links: [PDF] [Poster] @conference{anagnostopoulou2023realistic,
title = {A Realistic Synthetic Mushroom Scenes Dataset},
author = {D Anagnostopoulou and G Retsinas and N Efthymiou and P P Filntisis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Anagnostopoulou_CVPRW2023_paper.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Anagnostopoulou_CVPRW2023_poster.pdf},
year = {2023},
date = {2023-06-01},
booktitle = {Proc. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4th Agriculture Vision Workshop},
address = {Vancouver, Canada},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
P P Filntisis, G Retsinas, F Paraperas-Papantoniou, A Katsamanis, A Roussos, P Maragos SPECTRE: Visual Speech-Informed Perceptual 3D Facial Expression Reconstruction from Videos Conference Proc. 2023 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW), Vancouver, Canada, 2023. BibTeX | Links: [PDF] @conference{filntisis2023spectre,
title = {SPECTRE: Visual Speech-Informed Perceptual 3D Facial Expression Reconstruction from Videos},
author = {P P Filntisis and G Retsinas and F Paraperas-Papantoniou and A Katsamanis and A Roussos and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Filntisis_CVPRW2023_SPECTRE_Visual_Speech-Informed_Perceptual_3D_Facial_Expression_Reconstruction_From_Videos_paper.pdf},
year = {2023},
date = {2023-06-01},
booktitle = {Proc. 2023 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 5th Workshop and Competition on Affective Behavior Analysis in-the-wild (ABAW)},
address = {Vancouver, Canada},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
C O Tze, P P Filntisis, A -L Dimou, A Roussos, P Maragos Neural Sign Reenactor: Deep Photorealistic Sign Language Retargeting Conference Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), AI for Content Creation Workshop (AI4CC), Vancouver, Canada, 2023. BibTeX | Links: [PDF] [Poster] @conference{tze2023neural,
title = {Neural Sign Reenactor: Deep Photorealistic Sign Language Retargeting},
author = {C O Tze and P P Filntisis and A -L Dimou and A Roussos and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Tze_CVPRW2023_Neural_Sign_Reenactor_Paper.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Tze_CVPRW2023_Neural_Sign_Reenactor_Poster.pdf},
year = {2023},
date = {2023-06-01},
booktitle = {Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), AI for Content Creation Workshop (AI4CC)},
address = {Vancouver, Canada},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2022
|
N Efthymiou, P P Filntisis, P Koutras, A Tsiami, J Hadfield, G Potamianos, P Maragos ChildBot: Multi-robot perception and interaction with children Journal Article Robotics and Autonomous Systems, 150 , pp. 103975, 2022. BibTeX | Links: [PDF] @article{efthymiou2022childbot,
title = {ChildBot: Multi-robot perception and interaction with children},
author = {N Efthymiou and P P Filntisis and P Koutras and A Tsiami and J Hadfield and G Potamianos and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2022_EfthymiouEtAl_ChildBot-MultiRobotPerception-InteractionChildren_RAS.pdf},
doi = {10.1016/j.robot.2021.103975},
year = {2022},
date = {2022-01-01},
journal = {Robotics and Autonomous Systems},
volume = {150},
pages = {103975},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
A Zlatintsi, P P Filntisis, C Garoufis, N Efthymiou, P Maragos, A Manychtas, I Maglogiannis, P Tsanakas, T Sounapoglou, E Kalisperakis, T Karantinos, M Lazaridi, V Garyfali, A Mantas, L Mantonakis, N Smyrnis e-Prevention: Advanced Support System for Monitoring and Relapse Prevention in Patients with Psychotic Disorders Analysing Long-Term Multimodal Data from Wearables and Video Captures Journal Article Sensors, 22 (19), pp. 7544, 2022. BibTeX | Links: [PDF] @article{zlatintsi2022e-prevention,
title = {e-Prevention: Advanced Support System for Monitoring and Relapse Prevention in Patients with Psychotic Disorders Analysing Long-Term Multimodal Data from Wearables and Video Captures},
author = {A Zlatintsi and P P Filntisis and C Garoufis and N Efthymiou and P Maragos and A Manychtas and I Maglogiannis and P Tsanakas and T Sounapoglou and E Kalisperakis and T Karantinos and M Lazaridi and V Garyfali and A Mantas and L Mantonakis and N Smyrnis},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2022_ZlatintsiEtAl_EPrevention_SENSORS2022.pdf},
doi = {10.3390/s22197544},
year = {2022},
date = {2022-01-01},
journal = {Sensors},
volume = {22},
number = {19},
pages = {7544},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
C Garoufis, A Zlatintsi, P P Filntisis, N Efthymiou, E Kalisperakis, T Karantinos, V Garyfalli, M Lazaridi, N Smyrnis, P Maragos Towards Unsupervised Subject-Independent Speech-Based Relapse Detection in Patients with Psychosis using Variational Autoencoders Conference Proc. 30th European Signal Processing Conference (EUSIPCO), Belgrade, Serbia, 2022. BibTeX | Links: [PDF] [Slides] @conference{garoufis2022towards,
title = {Towards Unsupervised Subject-Independent Speech-Based Relapse Detection in Patients with Psychosis using Variational Autoencoders},
author = {C Garoufis and A Zlatintsi and P P Filntisis and N Efthymiou and E Kalisperakis and T Karantinos and V Garyfalli and M Lazaridi and N Smyrnis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2022_GaroufisEtAl_UnsupervisedSpeechBasedRelapseDetectionVAES_EUSIPCO2022.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Garoufis_SubjectIndependentRelapseDetectionAudioVAEs_EUSIPCO22_slides.pdf},
year = {2022},
date = {2022-09-01},
booktitle = {Proc. 30th European Signal Processing Conference (EUSIPCO)},
address = {Belgrade, Serbia},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
M Panagiotou, A Zlatintsi, P P Filntisis, A J Roumeliotis, N Efthymiou, P Maragos A Comparative Study of Autoencoder Architectures for Mental Health Analysis using Wearable Sensors Data Conference Proc. 30th European Signal Processing Conference (EUSIPCO), Belgrade, Serbia, 2022. BibTeX | Links: [PDF] [Slides] @conference{panagiotou2022comparative,
title = {A Comparative Study of Autoencoder Architectures for Mental Health Analysis using Wearable Sensors Data},
author = {M Panagiotou and A Zlatintsi and P P Filntisis and A J Roumeliotis and N Efthymiou and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2022_PanagiotouEtAl_ComStudyAutoencodersMentalHealthWearables_EUSIPCO2022.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Panagiotou_EUSIPCO2022_Presentation_slides.pdf},
year = {2022},
date = {2022-09-01},
booktitle = {Proc. 30th European Signal Processing Conference (EUSIPCO)},
address = {Belgrade, Serbia},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
F Paraperas-Papantoniou, P P Filntisis, P Maragos, A Roussos Neural Emotion Director: Speech-preserving semantic control of facial expressions in “in-the-wild” videos Conference Proc. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, USA, 2022, (CVPR-2022 Best Paper Finalist). BibTeX | Links: [PDF] [Poster] [Supp] @conference{paraperas2022neural,
title = {Neural Emotion Director: Speech-preserving semantic control of facial expressions in “in-the-wild” videos},
author = {F Paraperas-Papantoniou and P P Filntisis and P Maragos and A Roussos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Paraperas_NED-SpeechPreservingSemanticControlFacialExpressions_CVPR2022_paper.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Paraperas_cvpr2022_NED_poster.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Paraperas_NED_CVPR2022_supplemental-material.pdf},
year = {2022},
date = {2022-06-01},
booktitle = {Proc. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
address = {New Orleans, USA},
note = {CVPR-2022 Best Paper Finalist},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
C O Tze, P Filntisis, A Roussos, P Maragos Cartoonized Anonymization of Sign Language Videos Conference Proc. 14th IEEE Image, Video, and Multidimensional Signal Processing Workshop (IVMSP 2022), Nafplio, Greece, 2022. BibTeX | Links: [PDF] @conference{tze2022cartoonized,
title = {Cartoonized Anonymization of Sign Language Videos},
author = {C O Tze and P Filntisis and A Roussos and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Tze_IVMSP2022_Cartoonized-Anonymization-Sign-Videos_paper.pdf},
year = {2022},
date = {2022-06-01},
booktitle = {Proc. 14th IEEE Image, Video, and Multidimensional Signal Processing Workshop (IVMSP 2022)},
address = {Nafplio, Greece},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
G Retsinas, P Filntisis, N Kardaris, P Maragos Attribute-based Gesture Recognition: Generalization to Unseen Classes Conference Proc. 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP 2022), Nafplio, Greece, 2022. BibTeX | Links: [PDF] @conference{retsinas2022attribute,
title = {Attribute-based Gesture Recognition: Generalization to Unseen Classes},
author = {G Retsinas and P Filntisis and N Kardaris and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Retsinas_IVMSP2022_paper.pdf},
year = {2022},
date = {2022-06-01},
booktitle = {Proc. 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP 2022)},
address = {Nafplio, Greece},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2021
|
N Efthymiou, P P Filntisis, G Potamianos, P Maragos Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios Journal Article Technologies, 9 (4), pp. 86, 2021. BibTeX | Links: [PDF] @article{efthymiou2021visual,
title = {Visual Robotic Perception System with Incremental Learning for Child–Robot Interaction Scenarios},
author = {N Efthymiou and P P Filntisis and G Potamianos and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2021_EfthymiouEtAl_VisualRobotPerceptionSystem-ChildRobotInteract_Technologies-1.pdf},
doi = {10.3390/technologies9040086},
year = {2021},
date = {2021-01-01},
journal = {Technologies},
volume = {9},
number = {4},
pages = {86},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
|
P Antoniadis, P P Filntisis, P Maragos Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition Conference Proc. 16th IEEE Int’l Conf. on Automatic Face and Gesture Recognition (FG-2021), 2021. BibTeX | Links: [PDF] @conference{Antoniadis2021,
title = {Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition},
author = {P Antoniadis and P P Filntisis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2021_AntoniadisEtAl_Emotion-GCN-FacialExpressionRecogn_FG-1.pdf},
year = {2021},
date = {2021-12-01},
booktitle = {Proc. 16th IEEE Int’l Conf. on Automatic Face and Gesture Recognition (FG-2021)},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
I Pikoulis, P P Filntisis, P Maragos Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild Conference Proc. 16th IEEE Int’l Conf. on Automatic Face and Gesture Recognition (FG-2021), 2021. BibTeX | Links: [PDF] @conference{Pikoulis2021,
title = {Leveraging Semantic Scene Characteristics and Multi-Stream Convolutional Architectures in a Contextual Approach for Video-Based Visual Emotion Recognition in the Wild},
author = {I Pikoulis and P P Filntisis and P Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2021_PikoulisEtAl_VideoEmotionRecognInTheWild-SemanticMultiStreamContext_FG-1.pdf},
year = {2021},
date = {2021-12-01},
booktitle = {Proc. 16th IEEE Int’l Conf. on Automatic Face and Gesture Recognition (FG-2021)},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
P. P. Filntisis, N. Efthymiou, G. Potamianos,, P. Maragos An Audiovisual Child Emotion Recognition System for Child-Robot Interaction Applications Conference Proc. 29th European Signal Processing
Conference (EUSIPCO 2021), Dublin, Ireland, 2021. BibTeX | Links: [Slides] [PDF] @conference{Filntisis2021,
title = {An Audiovisual Child Emotion Recognition System for Child-Robot Interaction Applications},
author = {P. P. Filntisis, N. Efthymiou, G. Potamianos, and P. Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Filntisis_EUSIPCO2021_ChildEmotionRecogn_presentation_slides.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/2021_FilntisisEtAl_AV-ChildEmotionRecognSystem-ChildRobotInteract_EUSIPCO.pdf},
year = {2021},
date = {2021-08-31},
booktitle = {Proc. 29th European Signal Processing
Conference (EUSIPCO 2021)},
address = {Dublin, Ireland},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
C. Garoufis, A. Zlatintsi, P. P. Filntisis, N. Efthymiou, E. Kalisperakis, V. Garyfalli, T. Karantinos, L. Mantonakis, N. Smyrnis, P. Maragos An Unsupervised Learning Approach for Detecting Relapses from Spontaneous Speech in Patients with Psychosis Conference Proc. IEEE-EMBS International
Conference on Biomedical and Health Informatics (BHI-2021), 2021. BibTeX | Links: [PDF] [Poster] @conference{Garoufis2021b,
title = {An Unsupervised Learning Approach for Detecting Relapses from Spontaneous Speech in Patients with Psychosis},
author = {C. Garoufis, A. Zlatintsi, P. P. Filntisis, N. Efthymiou, E. Kalisperakis, V. Garyfalli, T. Karantinos, L. Mantonakis, N. Smyrnis and P. Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Garoufis_BHI2021_UnsupervisedLearningRelapseDetection_Paper.pdf
http://robotics.ntua.gr/wp-content/uploads/sites/2/Garoufis_BHI21_Poster.pdf},
year = {2021},
date = {2021-07-31},
booktitle = {Proc. IEEE-EMBS International
Conference on Biomedical and Health Informatics (BHI-2021)},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2020
|
P. P. Filntisis, N. Efthymiou, G. Potamianos, P. Maragos Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss Conference Proc. 16th European Computer Vision Conference Workshops (ECCVW) - Workshop on Bodily Expressed Emotion Understanding, 2020. BibTeX | Links: [PDF] [Code] @conference{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},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/Emotion_understanding_in_videos_through_body__context__and_visual_semantic_embedding_loss-1.pdf
https://github.com/filby89/NTUA-BEEU-eccv2020},
year = {2020},
date = {2020-08-01},
booktitle = {Proc. 16th European Computer Vision Conference Workshops (ECCVW) - Workshop on Bodily Expressed Emotion Understanding},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
I. Maglogiannis, A. Zlatintsi, A. Menychtas, D. Papadimatos, P.P. Filntisis, N. Efthymiou, G. Retsinas, P. Tsanakas,, P. Maragos 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 | Links: [PDF] @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},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2020_MaglogiannisEtAl_e-Prevention_IntelligentCloudPlatform_AIAI-1.pdf},
year = {2020},
date = {2020-06-04},
booktitle = {Int’l Conf. on Artificial Intelligence Applications and Innovation (AIAI-2020)},
address = {Halkidiki, Greece},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
G Retsinas, P P Filntisis, N Efthymiou, E Theodosis, A Zlatintsi, P Maragos 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 | Links: [PDF] @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},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/icassp2020_retsinas.pdf},
year = {2020},
date = {2020-05-01},
booktitle = {ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
pages = {3657-3661},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2019
|
P P Filntisis, N Efthymiou, P Koutras, G Potamianos, P Maragos 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 | Links: [PDF] @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},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/RAL_2019-5.pdf},
doi = {10.1109/LRA.2019.2930434},
year = {2019},
date = {2019-10-01},
journal = {IEEE Robotics and Automation Letters (with IROS option)},
volume = {4},
number = {4},
pages = {4011-4018},
abstract = {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.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
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. |
C. Garoufis, A. Zlatintsi, K. Kritsis, P.P. Filntisis, V. Katsouros, and P. Maragos
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 | Links: [PDF] @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
},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2019_GZKFKM_GestureInteractWithVirtualMusicInstrumentsForEducation_EUSIPCO-1-1.pdf},
year = {2019},
date = {2019-09-01},
booktitle = {Proc. 27th European Conf.(EUSIPCO-19)},
address = {A Coruna, Spain},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
2018
|
N. Efthymiou, P. Koutras, P. ~P. Filntisis, G. Potamianos, P. Maragos MULTI-VIEW FUSION FOR ACTION RECOGNITION IN CHILD-ROBOT INTERACTION Conference Proc. IEEE Int'l Conf. on Image Processing, Athens, Greece, 2018. Abstract | BibTeX | Links: [PDF] @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},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/EfthymiouKoutrasFilntisis_MultiViewFusActRecognChildRobotInteract_ICIP18.pdf},
year = {2018},
date = {2018-10-01},
booktitle = {Proc. IEEE Int'l Conf. on Image Processing},
address = {Athens, Greece},
abstract = {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.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
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. |
A. Zlatintsi, P.P. Filntisis, C. Garoufis, A. Tsiami, K. Kritsis, M.A. Kaliakatsos-Papakostas, A. Gkiokas, V. Katsouros, P. Maragos 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 | Links: [PDF] @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},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/ZlatintsiEtAl_WebBasedRealTimeKinectAppGestInteractVMI_ΑΜ18-1.pdf},
year = {2018},
date = {2018-09-01},
booktitle = {Proc. of Audio Mostly Conference (AM’18)},
address = {Wrexham, North Wales, UK},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
|
A Tsiami, P Koutras, Niki Efthymiou, P P Filntisis, G Potamianos, P Maragos 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 | Links: [PDF] @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},
url = {http://robotics.ntua.gr/wp-content/publications/2018_TsiamiEtAl_Multi3-MultisensorMultimodalChildInteractMultRobots_ICRA.pdf},
year = {2018},
date = {2018-05-01},
booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
address = {Brisbane, Australia},
abstract = {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.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
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. |
A Tsiami, P P Filntisis, N Efthymiou, P Koutras, G Potamianos, P Maragos 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 | Links: [PDF] @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},
url = {http://robotics.ntua.gr/wp-content/publications/2018_TsiamiEtAl_FarfieldAVperceptionHRI-ChildrenAdults_ICASSP.pdf},
year = {2018},
date = {2018-04-01},
booktitle = {Proc. IEEE Int'l Conf. Acous., Speech, and Signal Processing (ICASSP)},
address = {Calgary, Canada},
abstract = {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.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
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. |
2017
|
Panagiotis Paraskevas Filntisis, Athanasios Katsamanis, Pirros Tsiakoulis, Petros Maragos Video-realistic expressive audio-visual speech synthesis for the Greek language Journal Article Speech Communication, 95 , pp. 137–152, 2017, ISSN: 01676393. Abstract | BibTeX | Links: [PDF] @article{345,
title = {Video-realistic expressive audio-visual speech synthesis for the Greek language},
author = {Panagiotis Paraskevas Filntisis and Athanasios Katsamanis and Pirros Tsiakoulis and Petros Maragos},
url = {http://robotics.ntua.gr/wp-content/uploads/publications/FilntisisKatsamanisTsiakoulis+_VideoRealExprAudioVisSpeechSynthGrLang_SC17.pdf},
doi = {10.1016/j.specom.2017.08.011},
issn = {01676393},
year = {2017},
date = {2017-01-01},
journal = {Speech Communication},
volume = {95},
pages = {137--152},
abstract = {High quality expressive speech synthesis has been a long-standing goal towards natural human-computer interaction. Generating a talking head which is both realistic and expressive appears to be a considerable challenge, due to both the high complexity in the acoustic and visual streams and the large non-discrete number of emotional states we would like the talking head to be able to express. In order to cover all the desired emotions, a significant amount of data is required, which poses an additional time-consuming data collection challenge. In this paper we attempt to address the aforementioned problems in an audio-visual context. Towards this goal, we propose two deep neural network (DNN) architectures for Video-realistic Expressive Audio-Visual Text-To-Speech synthesis (EAVTTS) and evaluate them by comparing them directly both to traditional hidden Markov model (HMM) based EAVTTS, as well as a concatenative unit selection EAVTTS approach, both on the realism and the expressiveness of the generated talking head. Next, we investigate adaptation and interpolation techniques to address the problem of covering the large emotional space. We use HMM interpolation in order to generate different levels of intensity for an emotion, as well as investigate whether it is possible to generate speech with intermediate speaking styles between two emotions. In addition, we employ HMM adaptation to adapt an HMM-based system to another emotion using only a limited amount of adaptation data from the target emotion. We performed an extensive experimental evaluation on a medium sized audio-visual corpus covering three emotions, namely anger, sadness and happiness, as well as neutral reading style. Our results show that DNN-based models outperform HMMs and unit selection on both the realism and expressiveness of the generated talking heads, while in terms of adaptation we can successfully adapt an audio-visual HMM set trained on a neutral speaking style database to a target emotion. Finally, we show that HMM interpolation can indeed generate different levels of intensity for EAVTTS by interpolating an emotion with the neutral reading style, as well as in some cases, generate audio-visual speech with intermediate expressions between two emotions.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
High quality expressive speech synthesis has been a long-standing goal towards natural human-computer interaction. Generating a talking head which is both realistic and expressive appears to be a considerable challenge, due to both the high complexity in the acoustic and visual streams and the large non-discrete number of emotional states we would like the talking head to be able to express. In order to cover all the desired emotions, a significant amount of data is required, which poses an additional time-consuming data collection challenge. In this paper we attempt to address the aforementioned problems in an audio-visual context. Towards this goal, we propose two deep neural network (DNN) architectures for Video-realistic Expressive Audio-Visual Text-To-Speech synthesis (EAVTTS) and evaluate them by comparing them directly both to traditional hidden Markov model (HMM) based EAVTTS, as well as a concatenative unit selection EAVTTS approach, both on the realism and the expressiveness of the generated talking head. Next, we investigate adaptation and interpolation techniques to address the problem of covering the large emotional space. We use HMM interpolation in order to generate different levels of intensity for an emotion, as well as investigate whether it is possible to generate speech with intermediate speaking styles between two emotions. In addition, we employ HMM adaptation to adapt an HMM-based system to another emotion using only a limited amount of adaptation data from the target emotion. We performed an extensive experimental evaluation on a medium sized audio-visual corpus covering three emotions, namely anger, sadness and happiness, as well as neutral reading style. Our results show that DNN-based models outperform HMMs and unit selection on both the realism and expressiveness of the generated talking heads, while in terms of adaptation we can successfully adapt an audio-visual HMM set trained on a neutral speaking style database to a target emotion. Finally, we show that HMM interpolation can indeed generate different levels of intensity for EAVTTS by interpolating an emotion with the neutral reading style, as well as in some cases, generate audio-visual speech with intermediate expressions between two emotions. |
