Δημοσίευση ερευνητικού άρθρου σε περιοδικό ανοιχτής πρόσβασης
N. Gkalelis, D. Daskalakis, V. Mezaris, “ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network”, IEEE Access, vol. 10, pp. 108797-108816, 2022. DOI:10.1109/ACCESS.2022.3213652
In this paper a pure-attention bottom-up approach, called ViGAT, that utilizes an object detector together with a Vision Transformer (ViT) backbone network to derive object and frame features, and a head network to process these features for the task of event recognition and explanation in video, is proposed. The ViGAT head consists of graph attention network (GAT) blocks factorized along the spatial and temporal dimensions in order to capture effectively both local and long-term dependencies between objects or frames. Moreover, using the weighted in-degrees (WiDs) derived from the adjacency matrices at the various GAT blocks, we show that the proposed architecture can identify the most salient objects and frames that explain the decision of the network. A comprehensive evaluation study is performed, demonstrating that the proposed approach provides state-of-the-art results on three large, publicly available video datasets (FCVID, MiniKinetics, ActivityNet). Source code is made publicly available at: https://github.com/bmezaris/ViGAT
Παρουσίαση του έργου στο 11ο Πανελλήνιο Συνέδριο Μονάδων Κοινωνικής Φροντίδας «Επ’ Αρωγή» (εκτός προγράμματος)
Το 11ο Πανελλήνιο Συνέδριο Μονάδων Κοινωνικής Φροντίδας «Επ’Αρωγή» με θέμα: «Διαστάσεις, Δομές & Πρόσωπα της Φροντίδας» διοργανώθηκε από το Κέντρο Κοινωνικής Πρόνοιας Περιφέρειας Κρήτης στις 31 Οκτωβρίου και 1 Νοεμβρίου 2022, στο Κέντρο Αρχιτεκτονικής Μεσογείου, στα Χανιά. Στο συνέδριο παρουσιάστηκαν το αντικείμενο και οι στόχοι του έργου, ενώ μέσα από την παρουσίαση έγινε επίδειξη της δομής και της λειτουργικότητας του περιβάλλοντος χρήστη της ολοκληρωμένης διαδραστικής πλατφόρμας QuaLiSID που βρίσκεται υπό ανάπτυξη.
Δημοσίευση στο περιοδικό Electronics 2022
Apostolidis, K.; Mezaris, V.; Papadogiorgaki, M.; Bei, E.S.; Livanos, G.; Zervakis, M.E. Content and Other Resources Recommendations for Individuals with Intellectual Disability: A Review. Electronics 2022, 11, 3472. https://doi.org/10.3390/electronics11213472
In this review paper, we look into how a recommendation system can be adapted to and support people with intellectual disability (ID). We start by reviewing and comparing the main classes of techniques for general-purpose content recommendation. Then, centering on individuals with ID, we collect information on their special needs that may be relevant to or affected by content recommendation tasks. We review the few existing recommendation systems specifically designed or adapted to the needs of this population and finally, based on the reviewed literature sources, we catalog the traits that a future content recommendation system should have in order to respond well to the identified special needs. We hope this listing of desirable traits and future directions in our concluding sections will stimulate research towards opening the doors to the digital world for individuals with ID.
Παρουσίαση στο συνέδριο PETRA 2022
A. Grammatikopoulou, N. Grammalidis, M. Papadogiorgaki and M. Zervakis: A platform for health emergency warning and wandering behaviour detection supporting people with Intellectual Disability, The 15th ACM International Conference on PErvasive Technologies Related to Assistive Environments (PETRA 2022), June 29 – July 01, 2022, Corfu, Greece.
People with intellectual disabilities (ID) encounter several problems in their daily life, regarding the interaction with their environment, the communication with their caregivers and their mobility. Mobile and modern smartwatch applications have great potential to provide early warning for medical emergencies, such as fever, oxygen saturation decline and, recently, Covid-19 disease. Furthermore, such apps can also track their position, if necessary, and even automatically detect wandering behaviour. In this paper, we propose a platform that will be able to a) automatically recognize health emergency situations and/or detection of wandering behaviour based on smartwatch/smartphone sensors, b) provide appropriate notifications to both user and caregiver when needed. The final system is currently developed within a Greek national research project and a pilot implementation will be evaluated by a Greek assistive center for people with ID.
Παρουσίαση στο συνέδριο PETRA 2020
M. Papadogiorgaki, V. Mezaris, N. Grammalidis, K. Grigoriadis, E. S. Bei, G. Livanos, M. E. Zervakis: Quality of Life Support System for People with Intellectual Disability, Proceedings of the 13th ACM International Conference on Pervasive Technologies Related to Assistive Environments (PETRA 2020), June 2020, No 36, pp. 1-6.
People with intellectual disabilities (ID) encounter several problems regarding the interaction with their environment in terms of their daily needs, activities and communication. On this concept, an interactive support system with multiple functionalities is proposed, aiming at optimizing the opportunities provided to people with ID in order to cope with particular everyday issues. Specifically, it will provide information as well as entertainment, including creative and educational activities, through specialized learning programs. Additionally, it will automatically recognize health emergency situations, provide appropriate notifications, feature an emergency call button to contact the responsible caregivers, and support interaction using a specialized voice menu of instructions. The final system will be developed within a Greek research project and a pilot implementation will be evaluated by a Greek association of people with ID. The ultimate goal is to provide an affordable and user-friendly solution, tailored to the users’ needs.