@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}
}

@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}
}

@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}
}

@conference{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},
url = {http://robotics.ntua.gr/wp-content/uploads/sites/2/2018_HadfieldEtAl_ObjectAssemblyGuidance-ChildRobotInteraction_IROS.pdf},
year = {2018},
date = {2018-01-01},
booktitle = {2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
pages = {347--354},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}

@conference{ZKE+15,
title = {Quality Evaluation of Computational Models for Movie Summarization},
author = {A Zlatintsi and P Koutras and N Efthymiou and P Maragos and A Potamianos and K Pastra},
url = {http://robotics.ntua.gr/wp-content/publications/ZlatintsiEtAl_MovieSumEval-QoMEX2015.pdf},
year = {2015},
date = {2015-05-01},
address = {Costa Navarino, Messinia, Greece},
abstract = {In this paper we present a movie summarization system and we investigate what composes high quality movie summaries in terms of user experience evaluation. We propose state-of-the-art audio, visual and text techniques for the detection of perceptually salient events from movies. The evaluation of such computational models is usually based on the comparison of the similarity between the system-detected events and some ground-truth data. For this reason, we have developed the MovSum movie database, which includes sensory and semantic saliency annotation as well as cross-media relations, for objective evaluations. The automatically produced movie summaries were qualitatively evaluated, in an extensive human evaluation, in terms of informativeness and enjoyability accomplishing very high ratings up to 80% and 90%, respectively, which verifies the appropriateness of the proposed methods.},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}