Institution profile

University of Bologna

Academic institutioneurope · it
Official website
Research library593linked papers
Opportunities0open roles
Selected work

Representative Papers

Artificial intelligence in materials science and engineering: Current landscape, key challenges, and future trajectories

Jul 01, 2025Composite structures

Materials development faces significant challenges including data complexity, lengthy timelines, and low efficiency, necessitating intelligent approaches to accelerate discovery. This work provides a systematic review of artificial intelligence applications in materials science, integrating a spectrum of techniques from traditional machine learning to deep learning and generative AI. It focuses on representation methods and model construction for multimodal data—such as composition, structure, images, and text—and covers core algorithms including convolutional neural networks (CNNs), graph neural networks (GNNs), Transformers, and Gaussian processes. The review particularly highlights emerging directions such as uncertainty quantification, multi-source data fusion, and language-inspired representations, proposing a research pathway toward intelligent materials design. By offering a comprehensive AI framework, this study identifies critical challenges in data quality, standardization, and algorithmic adaptability, thereby significantly enhancing the efficiency and reliability of materials discovery and optimization.

10 citationsRead paper

A review of recent techniques for person re-identification

Dec 21, 2024Machine Vision and Applications

Supervised person re-identification (ReID) suffers from high annotation costs and poor generalizability, hindering large-scale deployment. This paper presents a systematic survey of supervised and unsupervised ReID advancements from 2020 to 2023, proposing a “dual-track comparative” analytical framework. It observes that supervised methods have approached performance saturation—achieving mAP >90% on standard benchmarks—while unsupervised approaches, leveraging clustering-based pseudo-labeling, cross-domain self-supervised pretraining, and attention-enhanced representation learning, have achieved over 25-percentage-point mAP gains on Market-1501 and DukeMTMC-reID, with several methods narrowing the gap to supervised baselines to less than 3%. Crucially, this work provides the first quantitative analysis of convergence trends for both paradigms, identifying key technical pathways—e.g., robust pseudo-label refinement, domain-adaptive contrastive learning, and uncertainty-aware clustering—as essential for transitioning unsupervised ReID toward practical deployment, while highlighting persistent open challenges in scalability, label noise resilience, and cross-scenario generalization.

6 citationsRead paper

An Automatic Deep Learning Approach for Trailer Generation through Large Language Models

Sep 12, 2024International Conference Frontiers Signal Processing

This work proposes an end-to-end framework for automatic movie trailer generation that integrates large language models (LLMs) with multimodal analysis to overcome the inefficiencies of traditional manual editing, which often struggles to produce content that is both narratively coherent and emotionally engaging. For the first time, LLMs are comprehensively leveraged across the entire pipeline—including key scene selection, highlight dialogue extraction, soundtrack generation, and voice-over synthesis—enabling synergistic co-creation across visual, textual, and audio modalities. Experimental results demonstrate that the proposed method outperforms state-of-the-art approaches in terms of narrative tension, visual appeal, and overall viewer experience.

4 citationsRead paper

Large datasets for the Euro Area and its member countries and the dynamic effects of the common monetary policy

Oct 07, 2024

This study investigates heterogeneous responses to common monetary policy shocks across Eurozone countries, focusing on asymmetric transmission mechanisms in prices, interest rates, real output, and equity prices. We construct and publicly release EA-MD-QD—a novel high-frequency macroeconomic database covering the Eurozone aggregate and ten member states, updated monthly/quarterly and continuously revised since January 2000 (comprising 800+ time series). Employing state-of-the-art methods—including Common Component VAR, instrumental variable estimation, and sign-restricted identification—we systematically uncover structural disparities in monetary transmission between core and peripheral countries, and demonstrate that real—not nominal—variables predominantly drive business cycle synchronization across members. Our key contributions are threefold: (i) the first integrated, high-frequency, publicly available Eurozone macrodatabase; (ii) the first empirical characterization of intra-Eurozone monetary policy transmission asymmetries; and (iii) identification of the underlying drivers of such asymmetries.

3 citationsRead paper

Preference Queries over Taxonomic Domains

Jun 01, 2021Proceedings of the VLDB Endowment

This paper addresses three key challenges in taxonomy-based multi-preference querying: preference conflicts, granularity mismatch, and non-transitivity. To tackle these, we propose a logic-driven preference optimization retrieval framework. First, we formalize a taxonomy-aware logical preference model grounded in ontological semantics. Second, we introduce two novel preference rewriting operators that enhance specificity while preserving transitivity. Third, we formally prove that only two preference interpretations simultaneously satisfy transitivity and minimal conflict, and based on this result, we design an original heuristic ranking mechanism. Extensive experiments on both synthetic and real-world datasets demonstrate significant improvements in result rationality and user satisfaction. Our approach establishes a verifiable, scalable paradigm for semantic retrieval under complex, heterogeneous preference constraints.

3 citationsRead paper
Recent publications

Latest Papers