122 citations · 383 across the 26 of their papers we have counts for
28 papers
KARAMEL: Knowledge-Aware Ranking for Multimodal Entity Linking in the Arts via Heterogeneous Graphs
Raffaele Scaringi, Alejandro Sierra-Múnera, Gennaro Vessio +2
Discovering and disambiguating entities from multimodal and heterogeneous data is a key challenge in discovery science, where relevant knowledge is often implicit and distributed a…
Physics-Informed Diffusion for Biomechanically Plausible 3D Sign Language Generation
Emanuele Colonna, Moises Diaz, Gennaro Vessio +2
Sign language production, which generates continuous 3D skeletal motion from spoken language input, must simultaneously satisfy two constraints: semantic fidelity, so that a deaf v…
Understanding How MLLMs Describe Artworks Using Token Activation Maps
Nicola Fanelli, Pasquale De Marinis, Raffaele Scaringi +3
Multimodal Large Language Models (MLLMs) describe artworks with remarkable fluency, yet the visual reasoning behind their outputs remains opaque. When an MLLM names a style, identi…
Analyzing the Correlation Between Hallucinations and Knowledge Conflicts in Large Language Models
Lucrezia Laraspata, Giovanna Castellano, Gennaro Vessio
Hallucinations -- factually incorrect or unverifiable outputs -- remain one of the most challenging limitations of Large Language Models (LLMs), especially in knowledge-intensive t…
Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment
Ivan Rinaldi, Matteo Mendula, Nicola Fanelli +4
Music generation has advanced markedly through multimodal deep learning, enabling models to synthesize audio from text and, more recently, from images. However, existing image-cond…
DistillFSS: Synthesizing Few-Shot Knowledge into a Lightweight Segmentation Model
Pasquale De Marinis, Pieter M. Blok, Uzay Kaymak +3
Cross-Domain Few-Shot Semantic Segmentation (CD-FSS) seeks to segment unknown classes in unseen domains using only a few annotated examples. This setting is inherently challenging:…
Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRA
Pasquale De Marinis, Gennaro Vessio, Giovanna Castellano
Few-shot semantic segmentation (FSS) aims to segment novel classes in query images using only a small annotated support set. While prior research has mainly focused on improving de…
Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design
Pasquale De Marinis, Uzay Kaymak, Rogier Brussee +2
Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely…
LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks
Gennaro Vessio
Deep neural networks typically rely on the representation produced by their final hidden layer to make predictions, implicitly assuming that this single vector fully captures the s…
Modeling and benchmarking quantum optical neurons for efficient neural computation
Andrea Andrisani, Gennaro Vessio, Fabrizio Sgobba +3
Quantum optical neurons (QONs) are emerging as promising computational units that leverage photonic interference to perform neural operations in an energy-efficient and physically…
ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval
Nicola Fanelli, Gennaro Vessio, Giovanna Castellano
Analyzing digitized artworks requires both visual interpretation and deep artistic, contextual, and historical knowledge. We introduce ArtSeek, a multimodal framework for art analy…
I Dream My Painting: Connecting MLLMs and Diffusion Models via Prompt Generation for Text-Guided Multi-Mask Inpainting
Nicola Fanelli, Gennaro Vessio, Giovanna Castellano
Inpainting focuses on filling missing or corrupted regions of an image to blend seamlessly with its surrounding content and style. While conditional diffusion models have proven ef…
Neural network modelling of kinematic and dynamic features for signature verification
Moises Diaz, Miguel A. Ferrer, Jose Juan Quintana +5
Online signature parameters, which are based on human characteristics, broaden the applicability of an automatic signature verifier. Although kinematic and dynamic features have pr…
RoWeeder: Unsupervised Weed Mapping through Crop-Row Detection
Pasquale De Marinis, Gennaro Vessio, Giovanna Castellano
Precision agriculture relies heavily on effective weed management to ensure robust crop yields. This study presents RoWeeder, an innovative framework for unsupervised weed mapping…
Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation
Ivan Rinaldi, Nicola Fanelli, Giovanna Castellano +1
Artificial Intelligence and generative models have revolutionized music creation, with many models leveraging textual or visual prompts for guidance. However, existing image-to-mus…
What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?
Lorenzo Loconte, Antonio Mari, Gennaro Gala +5
This paper establishes a rigorous connection between circuit representations and tensor factorizations, two seemingly distinct yet fundamentally related areas. By connecting these…
Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts
Pasquale De Marinis, Nicola Fanelli, Raffaele Scaringi +4
Few-shot semantic segmentation aims to segment objects from previously unseen classes using only a limited number of labeled examples. In this paper, we introduce Label Anything, a…
Dynamically enhanced static handwriting representation for Parkinson's disease detection
Moises Diaz, Miguel Angel Ferrer, Donato Impedovo +2
Computer aided diagnosis systems can provide non-invasive, low-cost tools to support clinicians. These systems have the potential to assist the diagnosis and monitoring of neurodeg…
Explainable offline automatic signature verifier to support forensic handwriting examiners
Moises Diaz, Miguel A. Ferrer, Gennaro Vessio
Signature verification is a critical task in many applications, including forensic science, legal judgments, and financial markets. However, current signature verification systems…
Density-based clustering with fully-convolutional networks for crowd flow detection from drones
Giovanna Castellano, Eugenio Cotardo, Corrado Mencar +1
Crowd analysis from drones has attracted increasing attention in recent times due to the ease of use and affordable cost of these devices. However, how this technology can provide…
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Dawei Du, Longyin Wen, Pengfei Zhu +52
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.…
A deep learning approach to clustering visual arts
Giovanna Castellano, Gennaro Vessio
Clustering artworks is difficult for several reasons. On the one hand, recognizing meaningful patterns based on domain knowledge and visual perception is extremely hard. On the oth…
Integrating Contextual Knowledge to Visual Features for Fine Art Classification
Giovanna Castellano, Giovanni Sansaro, Gennaro Vessio
Automatic art analysis has seen an ever-increasing interest from the pattern recognition and computer vision community. However, most of the current work is mainly based solely on…
Ensembling complex network 'perspectives' for mild cognitive impairment detection with artificial neural networks
Eufemia Lella, Gennaro Vessio
In this paper, we propose a novel method for mild cognitive impairment detection based on jointly exploiting the complex network and the neural network paradigm. In particular, the…