We present a generative neural language model for the most ancient proven stage of the Greek language, the Mycenaean Greek attributed by the Linear B script. To capture the statistical structure of the Mycenaean documents, we present a Bidirectional Recurrent Neural Network and compare it to the traditionally used n -grams. The model is used to supplement the damaged parts of the Mycenaean texts, namely the incomplete, to a greater or lesser extent, words, which are typically discovered on partially damaged clay tablets. We verify our method experimentally using ground-truth, then we demonstrate our results on real cases and compare with experts’ opinions. We also present a methodology to augment our dataset, which turns out to improve our results.
MuseLearn is a platform that enhances the presentation of the exhibits of a museum with multimedia-rich content 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 exhibits; 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. We present the systems and the initial results for a selected set of exhibits in Herakleidon Museum, a museum holding temporary exhibitions mainly about ancient Greek technology. The initial evaluation that we presented is encouraging for all systems. Thus, the plan is to use the developed systems for all museum exhibits as well as to enhance their functionality.
To identify any aircraft in the world, it is sufficient to read its registration number. This number is a unique identifier, and offers valuable information, in the same way a car registration number does. In this work, the authors present the results of their feasibility study towards a simple, yet very efficient and effective system to identify aircrafts using video‐optical character recognition acquired by off‐the‐shelf cameras. They used several videos under realistic conditions at the Heraklion airport during high season and they achieved very promising results. They claim that there is much room for the development of a low‐cost airport surface monitoring system based on standard cameras, which can complement high‐cost radars.
Sign language (SL) translation constitutes an extremely challenging task when undertaken in a general unconstrained setup, especially in the absence of vast training datasets that enable the use of end-to-end solutions employing deep architectures. In such cases, the ability to incorporate prior information can yield a significant improvement in the translation results by greatly restricting the search space of the potential solutions. In this work, we treat the translation problem in the limited confines of psychiatric interviews involving doctor-patient diagnostic sessions for deaf and hard of hearing patients with mental health problems.To overcome the lack of extensive training data and be able to improve the obtained translation performance, we follow a domain-specific approach combining data-driven feature extraction with the incorporation of prior information drawn from the available domain knowledge. This knowledge enables us to model the context of the interviews by using an appropriately defined hierarchical ontology for the contained dialogue, allowing for the classification of the current state of the interview, based on the doctor’s question. Utilizing this information, video transcription is treated as a sentence retrieval problem. The goal is predicting the patient’s sentence that has been signed in the SL video based on the available pool of possible responses, given the context of the current exchange. Our experimental evaluation using simulated scenarios of psychiatric interviews demonstrate the significant gains of incorporating context awareness in the system’s decisions.