Malware detection is increasingly challenged by evolving techniques like obfuscation and polymorphism, limiting the effectiveness of traditional methods. Meanwhile, the widespread adoption of software containers has introduced new security challenges, including the growing threat of malicious software injection, where a container, once compromised, can serve as entry point for further cyberattacks. In this work, we address these security issues by introducing a method to identify compromised containers through machine learning analysis of their file systems. We cast the entire software containers into large RGB images via their tarball representations, and propose to use established Convolutional Neural Network architectures on a streaming, patch-based manner. To support our experiments, we release the COSOCO dataset--the first of its kind--containing 3364 large-scale RGB images of benign and compromised software containers at this https URL Our method detects more malware and achieves higher F1 and Recall scores than all individual and ensembles of VirusTotal engines, demonstrating its effectiveness and setting a new standard for identifying malware-compromised software containers.

Automated X-ray inspection is crucial for efficient and unobtrusive security screening in various public settings. However, challenges such as object occlusion, variations in the physical properties of items, diversity in X-ray scanning devices, and limited training data hinder accurate and reliable detection of illicit items. Despite the large body of research in the field, reported experimental evaluations are often incomplete, with frequently conflicting outcomes. To shed light on the research landscape and facilitate further research, a systematic, detailed, and thorough comparative evaluation of recent Deep Learning (DL)-based methods for X-ray object detection is conducted. For this, a comprehensive evaluation framework is developed, composed of: a) Six recent, large-scale, and widely used public datasets for X-ray illicit item detection (OPIXray, CLCXray, SIXray, EDS, HiXray, and PIDray), b) Ten different state-of-the-art object detection schemes covering all main categories in the literature, including generic Convolutional Neural Network (CNN), custom CNN, generic transformer, and hybrid CNN-transformer architectures, and c) Various detection (mAP50 and mAP50:95) and time/computational-complexity (inference time (ms), parameter size (M), and computational load (GFLOPS)) metrics. A thorough analysis of the results leads to critical observations and insights, emphasizing key aspects such as: a) Overall behavior of the object detection schemes, b) Object-level detection performance, c) Dataset-specific observations, and d) Time efficiency and computational complexity analysis. To support reproducibility of the reported experimental results, the evaluation code and model weights are made publicly available at this https URL.

Explainable AI (XAI) is concerned with how to make AI models more understandable to people. To date these explanations have predominantly been technocentric - mechanistic or productivity oriented. This paper introduces the Explainable AI for the Arts (XAIxArts) manifesto to provoke new ways of thinking about explainability and AI beyond technocentric discourses. Manifestos offer a means to communicate ideas, amplify unheard voices, and foster reflection on practice. To supports the co-creation and revision of the XAIxArts manifesto we combine a World Caf\'e style discussion format with a living manifesto to question four core themes: 1) Empowerment, Inclusion, and Fairness; 2) Valuing Artistic Practice; 3) Hacking and Glitches; and 4) Openness. Through our interactive living manifesto experience we invite participants to actively engage in shaping this XIAxArts vision within the CHI community and beyond.

The rapid evolution of deep learning (DL) models and the ever-increasing size of available datasets have raised the interest of the research community in the always important field of visual hand gesture recognition (VHGR), and delivered a wide range of applications, such as sign language understanding and human-computer interaction using cameras. Despite the large volume of research works in the field, a structured and complete survey on VHGR is still missing, leaving researchers to navigate through hundreds of papers in order to find the right combination of data, model, and approach for each task. The current survey aims to fill this gap by presenting a comprehensive overview of this computer vision field. With a systematic research methodology that identifies the state-of-the-art works and a structured presentation of the various methods, datasets, and evaluation metrics, this review aims to constitute a useful guideline for researchers, helping them to choose the right strategy for handling a VHGR task. Starting with the methodology used to locate the related literature, the survey identifies and organizes the key VHGR approaches in a taxonomy-based format, and presents the various dimensions that affect the final method choice, such as input modality, task type, and application domain. The state-of-the-art techniques are grouped across three primary VHGR tasks: static gesture recognition, isolated dynamic gestures, and continuous gesture recognition. For each task, the architectural trends and learning strategies are listed. To support the experimental evaluation of future methods in the field, the study reviews commonly used datasets and presents the standard performance metrics. Our survey concludes by identifying the major challenges in VHGR, including both general computer vision issues and domain-specific obstacles, and outlines promising directions for future research.

Asynchronous communication has become increasingly essential in the context of extended reality (XR), enabling users to interact and share information immersively without the constraints of simultaneous engagement. However, current XR systems often struggle to support effective asynchronous interactions, mainly due to limitations in contextual replay and navigation. This paper aims to address these limitations by introducing a novel system that enhances asynchronous communication in XR through the concept of MemoryPods, which allow users to record, annotate, and replay interactions with spatial and temporal accuracy. MemoryPods also feature AI-driven summarisation to ease cognitive load. A user evaluation conducted in a remote maintenance scenario demonstrated significant improvements in comprehension, highlighting the system's potential to transform collaboration in XR. The findings suggest broad applicability of the proposed system across various domains, including direct messaging, healthcare, education, remote collaboration, and training, offering a promising solution to the complexities of asynchronous communication in immersive environments.

Autonomous Vehicles (AVs) use natural images and videos as input to understand the real world by overlaying and inferring digital elements, facilitating proactive detection in an effort to assure safety. A crucial aspect of this process is real-time, accurate object recognition through automatic scene analysis. While traditional methods primarily concentrate on 2D object detection, exploring 3D object detection, which involves projecting 3D bounding boxes into the three-dimensional environment, holds significance and can be notably enhanced using the AR ecosystem. This study examines an AI model's ability to deduce 3D bounding boxes in the context of real-time scene analysis while producing and evaluating the model's performance and processing time, in the virtual domain, which is then applied to AVs. This work also employs a synthetic dataset that includes artificially generated images mimicking various environmental, lighting, and spatiotemporal states. This evaluation is oriented in handling images featuring objects in diverse weather conditions, captured with varying camera settings. These variations pose more challenging detection and recognition scenarios, which the outcomes of this work can help achieve competitive results under most of the tested conditions.

Unmanned aerial vehicles (UAV) are used in precision agriculture (PA) to enable aerial monitoring of farmlands. Intelligent methods are required to pinpoint weed infestations and make optimal choice of pesticide. UAV can fly a multispectral camera and collect data. However, the classification of multispectral images using supervised machine learning algorithms such as convolutional neural networks (CNN) requires large amount of training data. This is a common drawback in deep learning we try to circumvent making use of a semi-supervised generative adversarial networks (GAN), providing a pixel-wise classification for all the acquired multispectral images. Our algorithm consists of a generator network that provides photo-realistic images as extra training data to a multi-class classifier, acting as a discriminator and trained on small amounts of labeled data. The performance of the proposed method is evaluated on the weedNet dataset consisting of multispectral crop and weed images collected by a micro aerial vehicle (MAV). The results by the proposed semi-supervised GAN achieves high classification accuracy and demonstrates the potential of GAN-based methods for the challenging task of multispectral image classification.

This paper studies convolutional neural networks (CNN) to learn unsupervised feature representations for 44 different plant species, collected at the Royal Botanic Gardens, Kew, England. To gain intuition on the chosen features from the CNN model (opposed to a 'black box' solution), a visualisation technique based on the deconvolutional networks (DN) is utilized. It is found that venations of different order have been chosen to uniquely represent each of the plant species. Experimental results using these CNN features with different classifiers show consistency and superiority compared to the state-of-the art solutions which rely on hand-crafted features.

Since the outbreak of the COVID-19 pandemic, many healthcare facilities have suffered from shortages in medical resources, particularly in Personal Protective Equipment (PPE). In this paper, we propose a game-theoretic approach to schedule PPE orders among healthcare facilities. In this PPE game, each independent healthcare facility optimises its own storage utilisation in order to keep its PPE cost at a minimum. Such a model can reduce peak demand considerably when applied to a variable PPE consumption profile. Experiments conducted for NHS England regions using actual data confirm that the challenge of securing PPE supply during disasters such as COVID-19 can be eased if proper stock management procedures are adopted. These procedures can include early stockpiling, increasing storage capacities and implementing measures that can prolong the time period between successive infection waves, such as social distancing measures. Simulation results suggest that the provision of PPE dedicated storage space can be a viable solution to avoid straining PPE supply chains in case a second wave of COVID-19 infections occurs.

As the security of public spaces remains a critical issue in today's world, Digital Twin technologies have emerged in recent years as a promising solution for detecting and predicting potential future threats. The applied methodology leverages a Digital Twin of a metro station in Athens, Greece, using the FlexSim simulation software. The model encompasses points of interest and passenger flows, and sets their corresponding parameters. These elements influence and allow the model to provide reasonable predictions on the security management of the station under various scenarios. Experimental tests are conducted with different configurations of surveillance cameras and optimizations of camera angles to evaluate the effectiveness of the space surveillance setup. The results show that the strategic positioning of surveillance cameras and the adjustment of their angles significantly improves the detection of suspicious behaviors and with the use of the DT it is possible to evaluate different scenarios and find the optimal camera setup for each case. In summary, this study highlights the value of Digital Twins in real-time simulation and data-driven security management. The proposed approach contributes to the ongoing development of smart security solutions for public spaces and provides an innovative framework for threat detection and prevention.

3D face reconstruction is a fundamental Computer Vision problem of extraordinary difficulty. Current systems often assume the availability of multiple facial images (sometimes from the same subject) as input, and must address a number of methodological challenges such as establishing dense correspondences across large facial poses, expressions, and non-uniform illumination. In general these methods require complex and inefficient pipelines for model building and fitting. In this work, we propose to address many of these limitations by training a Convolutional Neural Network (CNN) on an appropriate dataset consisting of 2D images and 3D facial models or scans. Our CNN works with just a single 2D facial image, does not require accurate alignment nor establishes dense correspondence between images, works for arbitrary facial poses and expressions, and can be used to reconstruct the whole 3D facial geometry (including the non-visible parts of the face) bypassing the construction (during training) and fitting (during testing) of a 3D Morphable Model. We achieve this via a simple CNN architecture that performs direct regression of a volumetric representation of the 3D facial geometry from a single 2D image. We also demonstrate how the related task of facial landmark localization can be incorporated into the proposed framework and help improve reconstruction quality, especially for the cases of large poses and facial expressions. Testing code will be made available online, along with pre-trained models this http URL

We provide in this paper a tutorial and a comprehensive survey of QoE management solutions in current and future networks. We start with a high level description of QoE management for multimedia services, which integrates QoE modelling, monitoring, and optimization. This followed by a discussion of HTTP Adaptive Streaming (HAS) solutions as the dominant technique for streaming videos over the best-effort Internet. We then summarize the key elements in SDN/NFV along with an overview of ongoing research projects, standardization activities and use cases related to SDN, NFV, and other emerging applications. We provide a survey of the state-of-the-art of QoE management techniques categorized into three different groups: a) QoE-aware/driven strategies using SDN and/or NFV; b) QoE-aware/driven approaches for adaptive streaming over emerging architectures such as multi-access edge computing, cloud/fog computing, and information-centric networking; and c) extended QoE management approaches in new domains such as immersive augmented and virtual reality, mulsemedia and video gaming applications. Based on the review, we present a list of identified future QoE management challenges regarding emerging multimedia applications, network management and orchestration, network slicing and collaborative service management in softwarized networks. Finally, we provide a discussion on future research directions with a focus on emerging research areas in QoE management, such as QoE-oriented business models, QoE-based big data strategies, and scalability issues in QoE optimization.

Precise knowledge about the size of a crowd, its density and flow can provide valuable information for safety and security applications, event planning, architectural design and to analyze consumer behavior. Creating a powerful machine learning model, to employ for such applications requires a large and highly accurate and reliable dataset. Unfortunately the existing crowd counting and density estimation benchmark datasets are not only limited in terms of their size, but also lack annotation, in general too time consuming to implement. This paper attempts to address this very issue through a content aware technique, uses combinations of Chan-Vese segmentation algorithm, two-dimensional Gaussian filter and brute-force nearest neighbor search. The results shows that by simply replacing the commonly used density map generators with the proposed method, higher level of accuracy can be achieved using the existing state of the art models.

Quality assessment is a key element for the evaluation of hardware and software involved in image and video acquisition, processing, and visualization. In the medical field, user-based quality assessment is still considered more reliable than objective methods, which allow the implementation of automated and more efficient solutions. Regardless of increasing research in this topic in the last decade, defining quality standards for medical content remains a non-trivial task, as the focus should be on the diagnostic value assessed from expert viewers rather than the perceived quality from na\"{i}ve viewers, and objective quality metrics should aim at estimating the first rather than the latter. In this paper, we present a survey of methodologies used for the objective quality assessment of medical images and videos, dividing them into visual quality-based and task-based approaches. Visual quality based methods compute a quality index directly from visual attributes, while task-based methods, being increasingly explored, measure the impact of quality impairments on the performance of a specific task. A discussion on the limitations of state-of-the-art research on this topic is also provided, along with future challenges to be addressed.

We introduce Dynamic Distinction Learning (DDL) for Video Anomaly Detection, a novel video anomaly detection methodology that combines pseudo-anomalies, dynamic anomaly weighting, and a distinction loss function to improve detection accuracy. By training on pseudo-anomalies, our approach adapts to the variability of normal and anomalous behaviors without fixed anomaly thresholds. Our model showcases superior performance on the Ped2, Avenue and ShanghaiTech datasets, where individual models are tailored for each scene. These achievements highlight DDL's effectiveness in advancing anomaly detection, offering a scalable and adaptable solution for video surveillance challenges.

In recent years, there has been an increasing interest in the use of artificial intelligence (AI) and extended reality (XR) in the beauty industry. In this paper, we present an AI-assisted skin care recommendation system integrated into an XR platform. The system uses a convolutional neural network (CNN) to analyse an individual's skin type and recommend personalised skin care products in an immersive and interactive manner. Our methodology involves collecting data from individuals through a questionnaire and conducting skin analysis using a provided facial image in an immersive environment. This data is then used to train the CNN model, which recognises the skin type and existing issues and allows the recommendation engine to suggest personalised skin care products. We evaluate our system in terms of the accuracy of the CNN model, which achieves an average score of 93% in correctly classifying existing skin issues. Being integrated into an XR system, this approach has the potential to significantly enhance the beauty industry by providing immersive and engaging experiences to users, leading to more efficient and consistent skincare routines.

In a recent series of papers, we proposed a mathematical model for the dynamics of a group of interacting pedestrians. The model is based on a non-Newtonian potential, that accounts for the need of pedestrians to keep both their interacting partner and their walking goal in their vision field, and to keep a comfortable distance between them. These two behaviours account respectively for the angular and radial part of the potential from which the force providing the pedestrian acceleration is derived. The angular term is asymmetric, i.e. does not follow the third law of dynamics, with observable effects on group formation and velocity. We successfully compared the predictions of the model with observations of real world pedestrian behaviour. We then studied the effect of crowd density on group dynamics. We verified that the average effect of crowd density may be modelled by adding a harmonic term to the group potential. The model predictions, which include "phase transitions" in the group configuration, are again confirmed, at least in the observed density range, by a comparison with real world data. Until now we had averaged all pedestrian data collected in a given environmental setting without differentiating on group composition and social roles. In this work we study how the group configuration and velocity is affected by inter-pedestrian relation (family, couples, colleagues, friends), purpose (work, leisure) and gender. We also show results related to the effect of asymmetric interactions, that confirm further the non-Newtonian nature of gaze-based angular interaction in our model.