Kosmas Kritsis

Chara Tsoukala, Kosmas Kritsis, Ioannis Douros, Athanasios Katsamanis, Nikolaos Kokkas, Vasileios Arampatzakis, Vasileios Sevetlidis, Stella Markantonatou, George Pavlidis. Proceedings of the Second Workshop on NLP Applications to Field Linguistics. 2023.

Automatically synthesizing dance motion sequences is an increasingly popular research task in the broader field of human motion analysis. Recent approaches have mostly used recurrent neural networks (RNNs), which are known to suffer from prediction error accumulation, usually limiting models to synthesize short choreographies of less than 100 poses. In this paper we present a multimodal convolutional autoencoder that combines 2D skeletal and audio information by employing an attention-based feature fusion mechanism, capable of generating novel dance motion sequences of arbitrary length. We first validate the ability of our system to capture the temporal context of dancing in a unimodal setting, by considering only skeletal features as input. According to 1440 rating answers provided by 24 participants in our initial user-study, we show that the optimal performance was presented by the model that was trained with input sequences of 500 poses. Based on this outcome, we train the proposed multimodal architecture with two different approaches, namely teacher-forcing and self-supervised curriculum learning, to deal with the autoregressive error accumulation phenomenon. In our evaluation campaign, we generate 1800 sequences and compare our method against two state-of-the-art approaches. Through qualitative and quantitative experiments we demonstrate the improvements introduced by the proposed multimodal architecture in terms of realism, motion diversity and multimodality, reducing the Fréchet Inception Distance (FID) metric value by 0.39. Subjective results confirm the effectiveness of our approach to synthesize diverse dance motion sequences, reporting a 6% increase in style consistency preference according to 1800 answers provided by 45 evaluators.

Tourism is a phenomenon that dates back to ancient times. Ancient Greek philosophers recognised, adopted, and promoted the concept of rest-based tourism. Ecotourism is a particular type of tourism that connects with activities that take place in nature, without harming it, along with the herbal and animal wealth. According to estimates, the global ecotourism industry is currently booming due to various reasons, and it is becoming an important factor of sustainable regional development. This article presents the vision, work, and outcomes of project AdVENt, a project focusing natively in sustainable ecotourism through natural science and technological innovation. AdVENt’s study area includes the National Parks of Oiti (or Oeta) and Parnassus in Central Greece, where there is a remarkable native flora with a high endemism rate integrated with areas of cultural value and national and European hiking routes and paths of varying difficulty.

Plant identification from images has become a rapidly developing research field in computer vision and is particularly challenging due to the morphological complexity of plants. The availability of large databases of plant images, and the research advancements in image processing, pattern recognition and machine learning, have resulted in a number of remarkably accurate and reliable image-based plant identification techniques, overcoming the time and expertise required for conventional plant identification, which is feasible only for expert botanists. In this paper, we introduce the GReek vAScular Plants (GRASP) dataset, a set of images composed of 125 classes of different species, for the automatic identification of vascular plants of Greece. In this context, we describe the methodology of data acquisition and dataset organization, along with the statistical features of the dataset. Furthermore, we present results of the application of popular deep learning architectures to the classification of the images in the dataset. Using transfer learning, we report 91% top-1 and 98% top-5 accuracy.

Jazz improvisation on a given lead sheet with chords is an interesting scenario for studying the behaviour of artificial agents when they collaborate with humans. Specifically in jazz improvisation, the role of the accompanist is crucial for reflecting the harmonic and metric characteristics of a jazz standard, while identifying in real-time the intentions of the soloist and adapt the accompanying performance parameters accordingly. This paper presents a study on a basic implementation of an artificial jazz accompanist, which provides accompanying chord voicings to a human soloist that is conditioned by the soloing input and the harmonic and metric information provided in a lead sheet chart. The model of the artificial agent includes a separate model for predicting the intentions of the human soloist, towards providing proper accompaniment to the human performer in real-time. Simple implementations of Recurrent Neural Networks are employed both for modeling the predictions of the artificial agent and for modeling the expectations of human intention. A publicly available dataset is modified with a probabilistic refinement process for including all the necessary information for the task at hand and test-case compositions on two jazz standards show the ability of the system to comply with the harmonic constraints within the chart. Furthermore, the system is indicated to be able to provide varying output with different soloing conditions, while there is no significant sacrifice of “musicality” in generated music, as shown in subjective evaluations. Some important limitations that need to be addressed for obtaining more informative results on the potential of the examined approach are also discussed.

This paper presents the iMuSciCA Workbench, developed to address secondary school students with the aim to support mastery of core academic content on Science, Technology, Engineering, Arts, and Mathematics (STEAM) subjects, along with the development of creativity and deeper learning skills through the students' participation in music activities. Herein, we focus on the technical implementation of the innovative music-related web environments hosted by the iMuSciCA Workbench.

Envisioned communication densities in Internet of Things applications are increasing continuously. Because these wireless devices are often battery powered, we need specific energy efficient (low-power) solutions. Moreover, these smart objects use low-cost hardware with possibly weak links, leading to a lossy network. Once deployed, these low-power lossy networks (LLNs) are intended to collect the expected measurements, handle transient faults, topology changes, etc. Consequently, validation and verification during the protocol development are a matter of prime importance. A large range of theoretical or practical tools are available for performance evaluation. A theoretical analysis may demonstrate that the performance guarantees are respected, while simulations or experiments aim on estimating the behaviour of a set of protocols within real-world scenarios. In this paper, we review the various parameters that should be taken into account during such a performance evaluation. Our primary purpose is to provide a tutorial that specifies guidelines for conducting performance evaluation campaigns of network protocols in LLNs. We detail the general approach adopted in order to evaluate the performance of layer 2 and 3 protocols in LLNs. Furthermore, we also specify the methodology that should be adopted during the performance evaluation, while reviewing the numerous models and tools that are available to the research community.