Επιστημονικές δημοσιεύσεις σε περιοδικά και συνέδρια οι οποίες προέκυψαν μέσω της υλοποίησης του έργου.
A cross-domain recommender system using deep coupled autoencoders
Alexandros Gkillas , Dimitrios Kosmopoulos, Member, IEEE

Abstract—Long-standing data sparsity and cold-start constitute thorny and perplexing problems for the recommendation systems. Cross-domain recommendation as a domain adaptation framework has been utilized to efficiently address these challenging issues, by exploiting information from multiple domains. In this study, an item-level relevance cross-domain recommendation task is explored, where two related domains, that is, the source and the target domain contain common items without sharing sensitive information regarding the users’ behavior, and thus avoiding the leak of user privacy. In light of this scenario, two novel coupled autoencoder-based deep learning methods are proposed for cross-domain recommendation. The first method aims to simultaneously learn a pair of autoencoders in order to reveal the intrinsic representations of the items in the source and target domains, along with a coupled mapping function to model the non-linear relationships between these representations, thus transferring beneficial information from the source to the target domain. The second method is derived based on a new joint regularized optimization problem, which employs two autoencoders to generate in a deep and non-linear manner the user and itemlatent factors, while at the same time a data-driven function is learnt to map the item-latent factors across domains. Extensive numerical experiments on two publicly available benchmark datasets are conducted illustrating the superior performance of our proposed methods compared to several state-of-the-art crossdomain recommendation frameworks.

Keywords: Index Terms—Cross-domain recommendation systems, coupled autoencoders, latent factor models, deep learning

Visitor behavior analysis for an ancient Greek technology exhibition
Dimitrios Kosmopoulos and Kali Tzortzi

Abstract: The paper reports the findings from research aimed at the analysis of visitor behavior in the Herakleidon Museum in Athens - Greece, which hosts an ancient Greek technology exhibition. Based on behavioral data gathered by direct observation, we aim to implement services to assist museum curators and enhance the visitors’ experience. We describe the data collection, analysis and prediction of the visitors’ preferences concerning the exhibits of the museum given their past preferences.

Keywords: museum visitor experience, recommendation systems

Toward Augmented Reality in Museums: Evaluation of Design Choices for 3D Object Pose Estimation
Paschalis Panteleris, Damien Michel and Antonis Argyros

Abstract—The solutions to many computer vision problems, including that of 6D object pose estimation, are dominated nowadays by the explosion of the learning-based paradigm. In this paper, we investigate 6D object pose estimation in a practical, real-word setting in which a mobile device (smartphone/tablet) needs to be localized in front of a museum exhibit, in support of an augmented-reality application scenario. In view of the constraints and the priorities set by this particular setting, we consider an appropriately tailored classical as well as a learning-based method. Moreover, we develop a hybrid method that consists of both classical and learning based components. All three methods are evaluated quantitatively on a standard, benchmark dataset, but also on a new dataset that is specific to the museum guidance scenario of interest.

Keywords: 3D object pose estimation, monocular RGB, templates, CNN, hybrid, method evaluation

The MuseLearn platform: personalized content for museum visitors assisted by visionbased recognition and 3D pose estimation of exhibits
Georgios Styliaras, Antonis Argiros, Constantinos Constantinopoulos, Dimitrios Kosmopoulos, Damien Michel, Paschalis Panteleris, Nota Pantzou, Katerina Papavasileiou, Georgios Styliaras, Kali Tzortzi

Abstract: MuseLearn is a platform that enhances the presentation of the exhibits of a museum with multimedia-rich content based on augmented reality that is adapted and recommended for certain visitor profiles and playbacks on their mobile devices. The platform consists mainly of a content management system that stores and prepares multimedia material for the presentation of exhibitsexhibits; a recommender system that monitors objectively the visitor's behavior so that it can further adapt the content to their needs; and a pose estimation system that identifies an exhibit and links it to the additional content that is prepared for it. This paper presents the systems and the initial results of their implementation and application for a set of exhibits in Herakleidon Museum, a museum holding temporary exhibitions mainly about ancient Greek technology. Initial evaluation is presented that is encouraging for all systems and will lead to further application of the systems in the museum for all exhibits and with enhanced functionality.

Keywords: Museum Guide System, Augmented reality, Recommender System, Pose estimation, Content Management System

A Dataset of Mycenaean Linear B Sequences
K. Papavasileiou , G. Owens, D. Kosmopoulos

Abstract: We present a dataset of Mycenaean Linear B sequences gathered from the Mycenaean inscriptions written in the 13th and 14th century B.C. (c. 1400-1200 B.C.). The dataset contains sequences of Mycenaean words and ideograms according to the rules of the Mycenaean Greek language in the Late Bronze Age. Our ultimate goal is to contribute to the study, reading and understanding of ancient scripts and languages. Focusing on sequences, we seek to exploit the structure of the entire language, not just the Mycenaean vocabulary, to analyse sequential patterns. We use the dataset to experiment on estimating the missing symbols in damaged inscriptions.

Keywords: Mycenaean Linear B script, sequential patterns

Το Έργο Muselearn: Μοντελοποίηση Επισκεπτών Σε Μουσεία Μέσω Τεχνητής Όρασης Και Μηχανικής Μάθησης Για Την Παροχή Στοχευόμενου Περιεχομένου Και Παιχνιδιών Επαυξημένης Πραγματικότητας
Δημήτριος Κοσμόπουλος, Αντώνης Αργυρός, Ιωάννης Λαδάς, Ελένη Νομικού

Περίληψη: Τα μουσεία αποτελούν διαχρονικά ίσως τους σημαντικότερους οργανισμούς για τη διαφύλαξη και προβολή της παγκόσμιας πολιτισμικής κληρονομιάς και εξαιρετικά σημαντικούς φορείς εκ παίδευσης και ανάπτυξης. Παρά τις σημαντικές εξελίξεις στην επιστήμη της μουσειολογίας και τους νέους τρόπους οργάνωσης, στα μουσεία συνήθως εφαρμόζονται οι παραδοσιακοί, γραμμικοί, μη διαδραστικοί τρόποι παρουσίασης των εκθεμάτων και εποπτικού υλικού, π.χ. ακουστική ξενάγηση ή κωδικοί QR που παραπέμπουν σε στατική πληροφορία. Πρόσφατα έχουν αρχίσει να αξιοποιούνται σύγχρονες διαδραστικές πολυμεσικές τεχνολογίες, που όμως απαιτούν σημαντική επένδυση από την πλευρά του μουσείου και συχνά έχουν περιορισμούς στην έκταση του υλικού αλλά και στο πλήθος των ανθρώπων που μπορούν να τα επισκεφθούν. Επίσης για την πλειονότητα των μουσείων δεν είναι σαφές πόσο ικανοποιημένοι είναι κάθε φορά οι επισκέπτες, πόσο τους ενδιέφεραν τα εκθέματα, το πρόσθετο ψηφιακό περιεχόμενο και ο τρόπος που παρουσιάζονται. Αντικείμενο του έργου ΜuseLearn είναι η ανάπτυξη πρότυπου συστήματος ξενάγησης σε μουσείο για κινητές συσκευές που θα παρέχει προσωποποιημένο πρόσθετο περιεχόμενο αξιοποιώντας τεχνικές εντοπισμού εκθεμάτων και παρακολούθησης επισκεπτών. Τελικό αποτέλεσμα θα είναι η αύξηση της ικανοποίησης των επισκεπτών και της επισκεψιμότητας του μουσείου.

A Survey on Developing Personalized Content Services in Museums
Dimitrios Kosmopoulos, Georgios Styliaras

Abstract: The personalized content services in museums are motivated by the need to enhance the visitors’ experience through recommendations which consider the context of their visit, and by the need of curators to measure objectively the exhibition’s impact. We survey the latest advancements in the fields of indoor localization, visitor profiling, content storage and presentation, as well as curator visualization tools, which are the main elements of such systems, and we highlight their strengths and weaknesses. We present an information architecture, which may offer useful insights to researchers and developers. Finally, we present the current challenges and the future trends.

Keywords: recommendations, museums, indoor localization, cultural heritage content, visualization, museum guides