arXiv subjects

Antonio Liotta

Publications and source records attributed to Antonio Liotta.

At least 19 recordsLinked to original sources

arXiv2026

SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation

Estimating human proficiency from video is a key challenge for automated skill assessment, with applications in sports coaching, music pedagogy, surgical training, and workplace learning. Existing approaches often focus on individual scenarios or rely on shared multi-view aggregation, limiting their ability to adapt to heterogeneous camera viewpoints and activity domains. We introduce SkillMoV, a unified, parameter-efficient framework for multi-scenario proficiency estimation from synchronized multi-view video. At its core, SkillMoV introduces a Mixture-of-View Projector (MoVP), which adapts the mixture-of-experts paradigm to camera-specific view features. MoVP is composed of four stages: (i) a Mixture-of-View soft router with twelve expert MLPs that learns view-dependent expert preferences without camera-identity supervision; (ii) cross-view attention to align synchronized cameras; (iii) learnable prototype anchoring to condition the representation on class-level reference vectors; and (iv) a prototype-conditioned gated projection that produces the final skill embedding. We evaluate SkillMoV on EgoExo4D across six skill domains and three separately trained view configurations: Ego, Exos, and Ego+Exos. SkillMoV reaches 50.17% overall accuracy in the Exos setting with a single model trained jointly across all scenarios, surpassing the strongest reported Exos result among the compared methods by 3.57 percentage points. In Ego+Exos, SkillMoV remains close to the best reported result in that setting (47.63% versus 48.20%). Ablations on the selected Exos configuration validate each component: MoV routing contributes +6.61 pp over attentive aggregation, cross-view attention +4.92 pp, prototype anchoring +4.07 pp, and stochastic view dropout +3.90 pp. Through LoRA adaptation, SkillMoV trains only 23.32% of its parameters and adds limited measured overhead relative to a LoRA-only baseline.

cs.CV↗

arXiv2026

Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback

Estimating how well a person performs an action, rather than which action is performed, is central to coaching, rehabilitation, and talent identification. This task is challenging because proficiency is encoded in subtle differences in timing, balance, body mechanics, and execution, often distributed across multiple views and short temporal events. We discuss three recent contributions to multi-view proficiency estimation on Ego-Exo4D. SkillFormer introduces a parameter-efficient discriminative architecture for selective multi-view fusion; PATS improves temporal sampling by preserving locally dense excerpts of fundamental movements; and ProfVLM reformulates proficiency estimation as conditional language generation, producing both a proficiency label and expert-style feedback through a gated cross-view projector and a compact language backbone. Together, these methods achieve state-of-the-art accuracy on Ego-Exo4D with up to 20x fewer trainable parameters and up to 3x fewer training epochs than video-transformer baselines, while moving from closed-set classification toward interpretable feedback generation. These results highlight a shift toward efficient, multi-view systems that combine selective fusion, proficiency-aware sampling, and actionable generative feedback.

cs.CV↗

arXiv2026

ProfVLM: A lightweight video-language model for multi-view proficiency estimation

Most existing approaches formulate action quality assessment and skill proficiency estimation as discriminative prediction tasks, typically producing discrete labels or scores without explicitly modeling the reasoning process underlying the assessment. We instead reformulate the problem as generative vision-language modeling, introducing ProfVLM, a parameter-efficient vision-language model that jointly predicts proficiency levels and generates expert-like natural language feedback from multi-view videos. ProfVLM leverages conditional language generation to provide actionable insights along with quantitative evaluation scores. Central to our method is an AttentiveGatedProjector that dynamically fuses and projects multi-view egocentric and exocentric features from a frozen TimeSformer backbone into a language model fine-tuned for feedback generation. Trained on EgoExo4D with expert commentaries, ProfVLM surpasses state-of-the-art methods while using up to 20x fewer parameters and reducing training time by up to 60% compared to existing classification-based methods. By providing natural language critiques aligned with performance levels, this work shows that generative vision-language modeling offers a powerful and efficient paradigm shift for interpretable action quality assessment.

cs.CV↗

arXiv2025

SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation

Assessing human skill levels in complex activities is a challenging problem with applications in sports, rehabilitation, and training. In this work, we present SkillFormer, a parameter-efficient architecture for unified multi-view proficiency estimation from egocentric and exocentric videos. Building on the TimeSformer backbone, SkillFormer introduces a CrossViewFusion module that fuses view-specific features using multi-head cross-attention, learnable gating, and adaptive self-calibration. We leverage Low-Rank Adaptation to fine-tune only a small subset of parameters, significantly reducing training costs. In fact, when evaluated on the EgoExo4D dataset, SkillFormer achieves state-of-the-art accuracy in multi-view settings while demonstrating remarkable computational efficiency, using 4.5x fewer parameters and requiring 3.75x fewer training epochs than prior baselines. It excels in multiple structured tasks, confirming the value of multi-view integration for fine-grained skill assessment. Project page at https://edowhite.github.io/SkillFormer

cs.CV↗

arXiv2025

PATS: Proficiency-Aware Temporal Sampling for Multi-View Sports Skill Assessment

Automated sports skill assessment requires capturing fundamental movement patterns that distinguish expert from novice performance, yet current video sampling methods disrupt the temporal continuity essential for proficiency evaluation. To this end, we introduce Proficiency-Aware Temporal Sampling (PATS), a novel sampling strategy that preserves complete fundamental movements within continuous temporal segments for multi-view skill assessment. PATS adaptively segments videos to ensure each analyzed portion contains full execution of critical performance components, repeating this process across multiple segments to maximize information coverage while maintaining temporal coherence. Evaluated on the EgoExo4D benchmark with SkillFormer, PATS surpasses the state-of-the-art accuracy across all viewing configurations (+0.65% to +3.05%) and delivers substantial gains in challenging domains (+26.22% bouldering, +2.39% music, +1.13% basketball). Systematic analysis reveals that PATS successfully adapts to diverse activity characteristics-from high-frequency sampling for dynamic sports to fine-grained segmentation for sequential skills-demonstrating its effectiveness as an adaptive approach to temporal sampling that advances automated skill assessment for real-world applications. Visit our project page at https://edowhite.github.io/PATS

cs.CV↗

arXiv2025

Sparse Self-Federated Learning for Energy Efficient Cooperative Intelligence in Society 5.0

Federated Learning offers privacy-preserving collaborative intelligence but struggles to meet the sustainability demands of emerging IoT ecosystems necessary for Society 5.0-a human-centered technological future balancing social advancement with environmental responsibility. The excessive communication bandwidth and computational resources required by traditional FL approaches make them environmentally unsustainable at scale, creating a fundamental conflict with green AI principles as billions of resource-constrained devices attempt to participate. To this end, we introduce Sparse Proximity-based Self-Federated Learning (SParSeFuL), a resource-aware approach that bridges this gap by combining aggregate computing for self-organization with neural network sparsification to reduce energy and bandwidth consumption.

cs.LG↗

arXiv2025

A Survey on RGB, 3D, and Multimodal Approaches for Unsupervised Industrial Image Anomaly Detection

In the advancement of industrial informatization, unsupervised anomaly detection technology effectively overcomes the scarcity of abnormal samples and significantly enhances the automation and reliability of smart manufacturing. As an important branch, industrial image anomaly detection focuses on automatically identifying visual anomalies in industrial scenarios (such as product surface defects, assembly errors, and equipment appearance anomalies) through computer vision techniques. With the rapid development of Unsupervised industrial Image Anomaly Detection (UIAD), excellent detection performance has been achieved not only in RGB setting but also in 3D and multimodal (RGB and 3D) settings. However, existing surveys primarily focus on UIAD tasks in RGB setting, with little discussion in 3D and multimodal settings. To address this gap, this artical provides a comprehensive review of UIAD tasks in the three modal settings. Specifically, we first introduce the task concept and process of UIAD. We then overview the research on UIAD in three modal settings (RGB, 3D, and multimodal), including datasets and methods, and review multimodal feature fusion strategies in multimodal setting. Finally, we summarize the main challenges faced by UIAD tasks in the three modal settings, and offer insights into future development directions, aiming to provide researchers with a comprehensive reference and offer new perspectives for the advancement of industrial informatization. Corresponding resources are available at https://github.com/Sunny5250/Awesome-Multi-Setting-UIAD.

cs.CV↗

arXiv2024

Modeling Resilience of Collaborative AI Systems

A Collaborative Artificial Intelligence System (CAIS) performs actions in collaboration with the human to achieve a common goal. CAISs can use a trained AI model to control human-system interaction, or they can use human interaction to dynamically learn from humans in an online fashion. In online learning with human feedback, the AI model evolves by monitoring human interaction through the system sensors in the learning state, and actuates the autonomous components of the CAIS based on the learning in the operational state. Therefore, any disruptive event affecting these sensors may affect the AI model's ability to make accurate decisions and degrade the CAIS performance. Consequently, it is of paramount importance for CAIS managers to be able to automatically track the system performance to understand the resilience of the CAIS upon such disruptive events. In this paper, we provide a new framework to model CAIS performance when the system experiences a disruptive event. With our framework, we introduce a model of performance evolution of CAIS. The model is equipped with a set of measures that aim to support CAIS managers in the decision process to achieve the required resilience of the system. We tested our framework on a real-world case study of a robot collaborating online with the human, when the system is experiencing a disruptive event. The case study shows that our framework can be adopted in CAIS and integrated into the online execution of the CAIS activities.

cs.SE↗

arXiv2023

GResilience: Trading Off Between the Greenness and the Resilience of Collaborative AI Systems

A Collaborative Artificial Intelligence System (CAIS) works with humans in a shared environment to achieve a common goal. To recover from a disruptive event that degrades its performance and ensures its resilience, a CAIS may then need to perform a set of actions either by the system, by the humans, or collaboratively together. As for any other system, recovery actions may cause energy adverse effects due to the additional required energy. Therefore, it is of paramount importance to understand which of the above actions can better trade-off between resilience and greenness. In this in-progress work, we propose an approach to automatically evaluate CAIS recovery actions for their ability to trade-off between the resilience and greenness of the system. We have also designed an experiment protocol and its application to a real CAIS demonstrator. Our approach aims to attack the problem from two perspectives: as a one-agent decision problem through optimization, which takes the decision based on the score of resilience and greenness, and as a two-agent decision problem through game theory, which takes the decision based on the payoff computed for resilience and greenness as two players of a cooperative game.

cs.SE↗

arXiv2023

Multivariate Time Series characterization and forecasting of VoIP traffic in real mobile networks

Predicting the behavior of real-time traffic (e.g., VoIP) in mobility scenarios could help the operators to better plan their network infrastructures and to optimize the allocation of resources. Accordingly, in this work the authors propose a forecasting analysis of crucial QoS/QoE descriptors (some of which neglected in the technical literature) of VoIP traffic in a real mobile environment. The problem is formulated in terms of a multivariate time series analysis. Such a formalization allows to discover and model the temporal relationships among various descriptors and to forecast their behaviors for future periods. Techniques such as Vector Autoregressive models and machine learning (deep-based and tree-based) approaches are employed and compared in terms of performance and time complexity, by reframing the multivariate time series problem into a supervised learning one. Moreover, a series of auxiliary analyses (stationarity, orthogonal impulse responses, etc.) are performed to discover the analytical structure of the time series and to provide deep insights about their relationships. The whole theoretical analysis has an experimental counterpart since a set of trials across a real-world LTE-Advanced environment has been performed to collect, post-process and analyze about 600,000 voice packets, organized per flow and differentiated per codec.

cs.NI↗

arXiv2022

A Systematic Review on Affective Computing: Emotion Models, Databases, and Recent Advances

Affective computing plays a key role in human-computer interactions, entertainment, teaching, safe driving, and multimedia integration. Major breakthroughs have been made recently in the areas of affective computing (i.e., emotion recognition and sentiment analysis). Affective computing is realized based on unimodal or multimodal data, primarily consisting of physical information (e.g., textual, audio, and visual data) and physiological signals (e.g., EEG and ECG signals). Physical-based affect recognition caters to more researchers due to multiple public databases. However, it is hard to reveal one's inner emotion hidden purposely from facial expressions, audio tones, body gestures, etc. Physiological signals can generate more precise and reliable emotional results; yet, the difficulty in acquiring physiological signals also hinders their practical application. Thus, the fusion of physical information and physiological signals can provide useful features of emotional states and lead to higher accuracy. Instead of focusing on one specific field of affective analysis, we systematically review recent advances in the affective computing, and taxonomize unimodal affect recognition as well as multimodal affective analysis. Firstly, we introduce two typical emotion models followed by commonly used databases for affective computing. Next, we survey and taxonomize state-of-the-art unimodal affect recognition and multimodal affective analysis in terms of their detailed architectures and performances. Finally, we discuss some important aspects on affective computing and their applications and conclude this review with an indication of the most promising future directions, such as the establishment of baseline dataset, fusion strategies for multimodal affective analysis, and unsupervised learning models.

cs.MM↗

arXiv2021

Correlation analysis of node and edge centrality measures in artificial complex networks

The importance of a node in a social network is identified through a set of measures called centrality. Degree centrality, closeness centrality, betweenness centrality and clustering coefficient are the most frequently used metrics to compute node centrality. Their computational complexity in some cases makes unfeasible, when not practically impossible, their computations. For this reason we focused on two alternative measures, WERW-Kpath and Game of Thieves, which are at the same time highly descriptive and computationally affordable. Our experiments show that a strong correlation exists between WERW-Kpath and Game of Thieves and the classical centrality measures. This may suggest the possibility of using them as useful and more economic replacements of the classical centrality measures.

cs.SI↗

arXiv2021

Cloud based Scalable Object Recognition from Video Streams using Orientation Fusion and Convolutional Neural Networks

Object recognition from live video streams comes with numerous challenges such as the variation in illumination conditions and poses. Convolutional neural networks (CNNs) have been widely used to perform intelligent visual object recognition. Yet, CNNs still suffer from severe accuracy degradation, particularly on illumination-variant datasets. To address this problem, we propose a new CNN method based on orientation fusion for visual object recognition. The proposed cloud-based video analytics system pioneers the use of bi-dimensional empirical mode decomposition to split a video frame into intrinsic mode functions (IMFs). We further propose these IMFs to endure Reisz transform to produce monogenic object components, which are in turn used for the training of CNNs. Past works have demonstrated how the object orientation component may be used to pursue accuracy levels as high as 93\%. Herein we demonstrate how a feature-fusion strategy of the orientation components leads to further improving visual recognition accuracy to 97\%. We also assess the scalability of our method, looking at both the number and the size of the video streams under scrutiny. We carry out extensive experimentation on the publicly available Yale dataset, including also a self generated video datasets, finding significant improvements (both in accuracy and scale), in comparison to AlexNet, LeNet and SE-ResNeXt, which are the three most commonly used deep learning models for visual object recognition and classification.

cs.CV↗

arXiv2021

Supervised Feature Selection Techniques in Network Intrusion Detection: a Critical Review

Machine Learning (ML) techniques are becoming an invaluable support for network intrusion detection, especially in revealing anomalous flows, which often hide cyber-threats. Typically, ML algorithms are exploited to classify/recognize data traffic on the basis of statistical features such as inter-arrival times, packets length distribution, mean number of flows, etc. Dealing with the vast diversity and number of features that typically characterize data traffic is a hard problem. This results in the following issues: i) the presence of so many features leads to lengthy training processes (particularly when features are highly correlated), while prediction accuracy does not proportionally improve; ii) some of the features may introduce bias during the classification process, particularly those that have scarce relation with the data traffic to be classified. To this end, by reducing the feature space and retaining only the most significant features, Feature Selection (FS) becomes a crucial pre-processing step in network management and, specifically, for the purposes of network intrusion detection. In this review paper, we complement other surveys in multiple ways: i) evaluating more recent datasets (updated w.r.t. obsolete KDD 99) by means of a designed-from-scratch Python-based procedure; ii) providing a synopsis of most credited FS approaches in the field of intrusion detection, including Multi-Objective Evolutionary techniques; iii) assessing various experimental analyses such as feature correlation, time complexity, and performance. Our comparisons offer useful guidelines to network/security managers who are considering the incorporation of ML concepts into network intrusion detection, where trade-offs between performance and resource consumption are crucial.

cs.CR↗

arXiv2021

Graph and Network Theory for the analysis of Criminal Networks

Social Network Analysis is the use of Network and Graph Theory to study social phenomena, which was found to be highly relevant in areas like Criminology. This chapter provides an overview of key methods and tools that may be used for the analysis of criminal networks, which are presented in a real-world case study. Starting from available juridical acts, we have extracted data on the interactions among suspects within two Sicilian Mafia clans, obtaining two weighted undirected graphs. Then, we have investigated the roles of these weights on the criminal network's properties, focusing on two key features: weight distribution and shortest path length. We also present an experiment that aims to construct an artificial network that mirrors criminal behaviours. To this end, we have conducted a comparative degree distribution analysis between the real criminal networks, using some of the most popular artificial network models: Watts-Strogatz, Erdős-Rényi, and Barabási-Albert, with some topology variations. This chapter will be a valuable tool for researchers who wish to employ social network analysis within their own area of interest.

cs.SI↗

arXiv2021

Criminal Networks Analysis in Missing Data scenarios through Graph Distances

Data collected in criminal investigations may suffer from: (i) incompleteness, due to the covert nature of criminal organisations; (ii) incorrectness, caused by either unintentional data collection errors and intentional deception by criminals; (iii) inconsistency, when the same information is collected into law enforcement databases multiple times, or in different formats. In this paper we analyse nine real criminal networks of different nature (i.e., Mafia networks, criminal street gangs and terrorist organizations) in order to quantify the impact of incomplete data and to determine which network type is most affected by it. The networks are firstly pruned following two specific methods: (i) random edges removal, simulating the scenario in which the Law Enforcement Agencies (LEAs) fail to intercept some calls, or to spot sporadic meetings among suspects; (ii) nodes removal, that catches the hypothesis in which some suspects cannot be intercepted or investigated. Finally we compute spectral (i.e., Adjacency, Laplacian and Normalised Laplacian Spectral Distances) and matrix (i.e., Root Euclidean Distance) distances between the complete and pruned networks, which we compare using statistical analysis. Our investigation identified two main features: first, the overall understanding of the criminal networks remains high even with incomplete data on criminal interactions (i.e., 10% removed edges); second, removing even a small fraction of suspects not investigated (i.e., 2% removed nodes) may lead to significant misinterpretation of the overall network.

cs.SI↗

arXiv2020

Correlations among Game of Thieves and other centrality measures in complex networks

Social Network Analysis (SNA) is used to study the exchange of resources among individuals, groups, or organizations. The role of individuals or connections in a network is described by a set of centrality metrics which represent one of the most important results of SNA. Degree, closeness, betweenness and clustering coefficient are the most used centrality measures. Their use is, however, severely hampered by their computation cost. This issue can be overcome by an algorithm called Game of Thieves (GoT). Thanks to this new algorithm, we can compute the importance of all elements in a network (i.e. vertices and edges), compared to the total number of vertices. This calculation is done not in a quadratic time, as when we use the classical methods, but in polylogarithmic time. Starting from this we present our results on the correlation existing between GoT and the most widely used centrality measures. From our experiments emerge that a strong correlation exists, which makes GoT eligible as a centrality measure for large scale complex networks.

cs.SI↗

arXiv2020

Statistical Assessment of IP Multimedia Subsystem in a Softwarized Environment: a Queueing Networks Approach

The Next Generation 5G Networks can greatly benefit from the synergy between virtualization paradigms, such as the Network Function Virtualization (NFV), and service provisioning platforms such as the IP Multimedia Subsystem (IMS). The NFV concept is evolving towards a lightweight solution based on containers that, by contrast to classic virtual machines, do not carry a whole operating system and result in more efficient and scalable deployments. On the other hand, IMS has become an integral part of the 5G core network, for instance, to provide advanced services like Voice over LTE (VoLTE). In this paper we combine these virtualization and service provisioning concepts, deriving a containerized IMS infrastructure, dubbed cIMS, providing its assessment through statistical characterization and experimental measurements. Specifically, we: i) model cIMS through the queueing networks methodology to characterize the utilization of virtual resources under constrained conditions; ii) draw an extended version of the Pollaczek-Khinchin formula, which is useful to deal with bulk arrivals; iii) afford an optimization problem focused at maximizing the whole cIMS performance in the presence of capacity constraints, thus providing new means for the service provider to manage service level agreements (SLAs); $iv)$ evaluate a range of cIMS scenarios, considering different queuing disciplines including also multiple job classes. An experimental testbed based on the open source platform Clearwater has been deployed to derive some realistic values of key parameters (e.g. arrival and service times).

cs.NI↗