Vasileios Argyriou

Emotion recognition and generation have become increasingly important research areas in artificial intelligence, underpinning applications in healthcare, education, customer service, and human–computer interaction. Human emotion is inherently multimodal, being conveyed through facial expressions, speech, and language, while modern affective AI systems increasingly integrate these complementary modalities to improve robustness and expressiveness. Furthermore, emotion recognition and generation are becoming increasingly interconnected, with recognition models frequently supporting the training, control, and evaluation of generative systems, yet existing surveys typically examine these tasks independently or focus on individual modalities. This survey provides a comprehensive review of state-of-the-art methodologies for emotion recognition and generation across facial, speech, and textual modalities, covering preprocessing techniques, datasets, deep learning architectures, evaluation metrics, and emotion control mechanisms. Recent advances are categorised according to their underlying methodological approaches, enabling a systematic comparison of current techniques, their strengths, and their limitations. The quantitative comparisons show that Transformer-based Poster++ achieved 92% accuracy on RAF-DB, while XLM-EMO obtained an F1 score and accuracy of 0.85 on Affect in Tweets. For speech emotion recognition, the highest reported accuracy on RAVDESS was 92.88%. Among facial expression generation methods, EAT achieved an emotion-recognition accuracy of 75.43% on MEAD. For speech emotion generation, Seq2seq-VC obtained the lowest word error rate and equal error rate on VCTK, at 2.9% and 1.0%, respectively, while the diffusion-based DDDM-VC achieved the lowest character error rate of 1.0% on VCTK. These results indicate strong performance by Transformer-based facial and textual emotion-recognition methods; however, no single architectural family demonstrates consistent superiority across the reported generation metrics, datasets, and evaluation settings. Finally, the survey discusses current challenges and future research directions, providing a unified perspective on the development of multimodal affective AI systems.

Facial Expression Recognition (FER) has progressed rapidly over the last decade, driven by the transition from handcrafted descriptors and shallow classifiers to deep convolutional, attention-based, vision--language, and foundation-model architectures, and by the parallel growth of large-scale in-the-wild benchmarks covering categorical, dimensional, compound, micro-expression, Action Unit (AU), and intensity-estimation tasks. Despite this progress, the deep learning-based FER landscape has so far been reviewed only along narrow task-, architecture-, or application-specific axes, and a holistic, systematically organized account of its most recent advancements is still missing. This survey addresses this gap by providing a comprehensive review of recent deep learning-based FER, with explicit links to the wider Facial Affect Recognition (FAR) domain. Its main contributions are: a) A description of the evolution of FER research into five distinct phases, from handcrafted features and classical machine learning to attention-based, vision--language, and foundation-model approaches, together with the key milestone works of each phase; b) A multi-criteria taxonomy that systematically analyzes the literature along seven complementary criteria, namely the targeted recognition task, the input modality, the face analysis pre-processing pipeline, the underlying neural network architecture, the employed learning strategy, the acquisition setting, and the targeted application domain; c) A per-criterion comparative analysis of the literature, accompanied by critical insights into the relative strengths and limitations of the various categories of approaches under in-the-wild conditions; d) A task-organized review of the public datasets available for FER, together with a structured discussion of the corresponding annotation schemes, modalities, and evaluation protocols; e) A systematic compilation of the performance metrics adopted in the FER literature and a per task quantitative comparison of representative state-of-the-art deep learning methods on the most widely adopted benchmarks; and f) A comprehensive discussion of the current challenges and the most promising future research directions of the field, spanning data and annotation, generalization and robustness, representation and temporal modeling, computation and deployment, evaluation, and trustworthiness, fairness, and ethical aspects.

The ever increasing intensity and number of disasters make even more difficult the work of First Responders (FRs). Artificial intelligence and robotics solutions could facilitate their operations, compensating these difficulties. To this end, we propose a dataset for gesture-based UGV control by FRs, introducing a set of 12 commands, drawing inspiration from existing gestures used by FRs and tactical hand signals and refined after incorporating feedback from experienced FRs. Then we proceed with the data collection itself, resulting in 3312 RGBD pairs captured from 2 viewpoints and 7 distances. To the best of our knowledge, this is the first dataset especially intended for gesture-based UGV guidance by FRs. Finally we define evaluation protocols for our RGBD dataset, termed FR-GESTURE, and we perform baseline experiments, which are put forward for improvement. We have made data publicly available to promote future research on the domain: https://doi.org/10.5281/zenodo.18131333.

Automated X-ray inspection is crucial for efficient and unobtrusive security screening in various public settings. However, challenges such as object occlusion/overlap, variations in the physical properties of the items of interest, diversity in the types of X-ray scanning devices used, and limited training data hinder accurate and reliable detection of illicit items. Despite the large body of research works in the field, the reported experimental evaluation is often incomplete, while the derived outcomes are frequently conflicting. In order to shed light on the research landscape of this field and to facilitate further research, a systematic, detailed, and thorough comparative evaluation study of recent Deep Learning (DL)-based methods for X-ray object detection is conducted in this work. For achieving this, a comprehensive evaluation framework is developed, composed of the following building blocks: a) Six of the most recent, large-scale and widely used public datasets for X-ray illicit item detection (namely, OPIXray, CLCXray, SIXray, EDS, HiXray, and PIDray), b) Ten different state-of-the-art object detection schemes, covering all main categories present in the literature, including generic Convolutional Neural Network (CNN), custom (X-ray-specific) CNN, generic transformer and generic hybrid CNN-transformer architectures, and c) Various detection (mAP⁵⁰ and mAP^50:95 mean Average Precision (mAP)) and time/computational-complexity (inference time (ms), parameter size (M), and computational load (GFLOPS)) performance metrics. A thorough analysis of the computed experimental results leads to the extraction of critical observations and detailed insights, emphasizing on the following key aspects: a) Overall behavior of the various object detection schemes, b) Object-level detection performance investigation, c) Dataset-specific observations, d) Statistical variance and empirical reliability examination, and e) Time efficiency and computational complexity analysis. In order to support reproducibility of the reported experimental results and to promote research in the field, the evaluation framework code and model weights are publicly available at https://github.com/jgenc/xray-comparative-evaluation, while a broad set of precomputed results (for all employed detectors and datasets) can be found at https://jgenc.github.io/ceasefire_demo/#/.

This study examines the impact of health expenditure on economic growth in the BRICS countries during the period 2000–2021. Economic growth is measured by GDP per capita, while per capita health expenditure serves as the principal explanatory variable. Consistent with the framework of endogenous growth theory—which conceptualizes health as a form of human capital that enhances productivity—we additionally incorporate natural capital, education, and population share as control variables. Methodologically, the analysis employs panel unit root tests under cross-sectional dependence and estimates a dynamic panel ARDL model to assess both short- and long-term effects. To further validate the robustness of the model, additional explanatory variables relevant to endogenous growth theory are also evaluated. The results indicate that, in the long run, all explanatory variables exert a statistically significant influence on the economic growth of the BRICS countries. In the short run, however, only per capita health expenditure demonstrates a positive and statistically significant effect on GDP per capita, whereas the other variables do not yield significant short-term effects.

The integration of Unmanned Aerial Vehicles (UAVs) and Low-Earth Orbit (LEO) satellites as aerial nodes in non-terrestrial networks (NTNs) presents both opportunities and challenges for on-demand 6G interconnectivity. This paper presents a new Composite Cost Metric (CCM) which improves energy-efficient routing performance in combined UAV-satellite constellations. We consider incorporating cumulative Free Space Path Loss (FSPL) and residual energy into the route selection process for both proactive and reactive protocols, our approach refines the routing decisions of classical protocols. The proposed CCM-driven modifications and protocol-specific integration typologies can improve overall route stability, reduce energy consumption per delivered packet, and optimize network reliability by dynamically selecting relays with lower attenuation and higher energy availability. We develop an NS-3-based simulation framework that integrates realistic satellite orbital mechanics, UAV mobility models, and a hybrid energy model that includes solar energy harvesting for satellites. Simulation results demonstrate that our enhancements can indeed outperform baseline implementations in packet delivery ratio, energy efficiency, and end-to-end delay which makes them viable for next-generation NTN-supported 6G networks, at the expense of some additional control overhead. With this set of developments we aim to pave the way for global-optimum and energy-aware emergency and disaster relief communications.