arXiv subjects

Giovanna Castellano

Publications and source records attributed to Giovanna Castellano.

At least 19 recordsLinked to original sources

arXiv2026

Physics-Informed Diffusion for Biomechanically Plausible 3D Sign Language Generation

Sign language production, which generates continuous 3D skeletal motion from spoken language input, must simultaneously satisfy two constraints: semantic fidelity, so that a deaf viewer can recognize the intended sequence of glosses, and biomechanical plausibility, so that the generated skeleton respects anatomical constraints. Existing approaches optimize semantic reconstruction through coordinate-based objectives that treat the skeleton as an unstructured vector, thus allowing for bone length drift, joint angle violations, and temporarily locked fingers. We introduce PIDiffSign, a physics-informed diffusion model for gloss-to-pose translation that incorporates anatomical constraints into both the architecture and training objective. The model uses a Transformer encoder-decoder, where the decoder is conditioned on the diffusion time step through adaptive zero-initialized layer normalization and cross-attends to gloss representations. A differentiable geometry module enforces bone length consistency and biologically valid joint angles throughout generation. Training combines anthropomorphic, kinematic, angular, and finger-joint constraints with a contrastive gloss-pose alignment loss and classifier-free guidance for semantically conditioned sampling. Experiments on the PHOENIX14T and CSL-Daily benchmarks show consistent improvements over a strong diffusion baseline in pose accuracy, joint-angle correctness, distributional realism, and back-translation quality. These results demonstrate that physics-informed diffusion improves both motion realism and semantic fidelity for sign language generation.

cs.CV↗

arXiv2026

Understanding How MLLMs Describe Artworks Using Token Activation Maps

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, identifies a subject, or recognizes an iconographic symbol, does it ground each claim in the relevant region of the canvas, draw on an undifferentiated visual signal, or rely primarily on textual priors? We study this using the Token Activation Map (TAM), which produces, for each generated token, a heatmap isolating the visual evidence specific to that token from prior-context interference. Applying TAM to a curated set of paintings spanning multiple periods and genres, we analyze grounding patterns across five semantically distinct token categories: common visual objects, style descriptors, metadata, iconographic tokens, and affective expressions. We find that visual grounding varies substantially with token semantics. We further show that MLLMs attempt to identify artworks and artists, achieving higher accuracy in artist attribution than in title prediction, where hallucinations are more frequent. Finally, we compare TAM with SAM~3 open-vocabulary segmentation. To ensure reproducibility, we release our code, experimental configurations, prompts, and qualitative results on the project page at https://nicolafan.github.io/tamart/.

cs.CV↗

arXiv2026

Analyzing the Correlation Between Hallucinations and Knowledge Conflicts in Large Language Models

Hallucinations -- factually incorrect or unverifiable outputs -- remain one of the most challenging limitations of Large Language Models (LLMs), especially in knowledge-intensive tasks. One proposed explanation is internal knowledge conflicts arising from fixed, outdated training data. This paper investigates whether internal representations linked to knowledge conflicts correlate with hallucination behaviors in LLMs. Using probing techniques inspired by two prior works, we analyzed activations from hidden, attention, and MLP layers, as well as output logits, across predefined tasks. We probed LLaMA-3-8B on hallucination detection benchmarks and Falcon-7B on a knowledge conflict dataset. Our findings show that, although conceptually related, hallucination activation patterns cannot be fully reduced to or explained by knowledge conflict representations. Nonetheless, probing proves a robust tool across multiple languages and activation types, supporting its role in improving LLM interpretability. This work advances the broader understanding of hallucinations in LLMs and underscores the value of fine-grained analysis of their internal behavior.

cs.CL↗

arXiv2026

Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRA

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 decoders, the encoder's limited ability to extract meaningful features for unseen classes remains a key bottleneck. In this work, we introduce \textit{Take a Peek} (TaP), a simple yet effective method that enhances encoder adaptability for both FSS and cross-domain FSS \rev{by inducing a lightweight \textit{feature-space shift} conditioned on the support set}. TaP leverages Low-Rank Adaptation to fine-tune the encoder on the support set with minimal computational overhead, enabling fast adaptation to novel classes while mitigating catastrophic forgetting. Our method is model-agnostic and can be seamlessly integrated into existing FSS pipelines. Extensive experiments across multiple benchmarks--including COCO $20^i$, Pascal $5^i$, and cross-domain datasets such as DeepGlobe, ISIC, and Chest X-ray--demonstrate that TaP consistently improves segmentation performance across diverse models and shot settings. Notably, TaP delivers significant gains in complex multi-class scenarios, highlighting its practical effectiveness in realistic settings. A rank sensitivity analysis also shows that strong performance can be achieved even with low-rank adaptations, thereby ensuring computational efficiency. By addressing a critical limitation in FSS--the encoder's generalization to novel classes--TaP paves the way toward more robust, efficient, and generalizable segmentation systems. The code is available at https://github.com/pasqualedem/TakeAPeek.

cs.CV↗

arXiv2026

Modeling and benchmarking quantum optical neurons for efficient neural computation

Quantum optical neurons (QONs) are emerging as promising computational units that leverage photonic interference to perform neural operations in an energy-efficient and physically grounded manner. Building on recent theoretical proposals, we introduce a family of QON architectures based on Hong-Ou-Mandel (HOM) and Mach-Zehnder (MZ) interferometers, incorporating different photon modulation strategies -- phase, amplitude, and intensity. These physical setups yield distinct pre-activation functions, which we implement as fully differentiable software modules. We evaluate these QONs both in isolation and as building blocks of multilayer networks, training them on binary and multiclass image classification tasks using the MNIST and FashionMNIST datasets. Each experiment is repeated over five independent runs and assessed under both ideal and non-ideal conditions to measure accuracy, convergence, and robustness. Across settings, MZ-based neurons exhibit consistently stable behavior -- including under noise -- while HOM amplitude modulation performs competitively in deeper architectures, in several cases approaching classical performance. In contrast, phase- and intensity-modulated HOM-based variants show reduced stability and greater sensitivity to perturbations. These results highlight the potential of QONs as efficient and scalable components for future quantum-inspired neural architectures and hybrid photonic-electronic systems. The code is publicly available at https://github.com/gvessio/quantum-optical-neurons.

physics.optics↗

arXiv2026

Art2Mus: Artwork-to-Music Generation via Visual Conditioning and Large-Scale Cross-Modal Alignment

Music generation has advanced markedly through multimodal deep learning, enabling models to synthesize audio from text and, more recently, from images. However, existing image-conditioned systems suffer from two fundamental limitations: (i) they are typically trained on natural photographs, limiting their ability to capture the richer semantic, stylistic, and cultural content of artworks; and (ii) most rely on an image-to-text conversion stage, using language as a semantic shortcut that simplifies conditioning but prevents direct visual-to-audio learning. Motivated by these gaps, we introduce ArtSound, a large-scale multimodal dataset of 105,884 artwork-music pairs enriched with dual-modality captions, obtained by extending ArtGraph and the Free Music Archive. We further propose ArtToMus, the first framework explicitly designed for direct artwork-to-music generation, which maps digitized artworks to music without image-to-text translation or language-based semantic supervision. The framework projects visual embeddings into the conditioning space of a latent diffusion model, enabling music synthesis guided solely by visual information. Experimental results show that ArtToMus generates musically coherent and stylistically consistent outputs that reflect salient visual cues of the source artworks. While absolute alignment scores remain lower than those of text-conditioned systems-as expected given the substantially increased difficulty of removing linguistic supervision-ArtToMus achieves competitive perceptual quality and meaningful cross-modal correspondence. This work establishes direct visual-to-music generation as a distinct and challenging research direction, and provides resources that support applications in multimedia art, cultural heritage, and AI-assisted creative practice. Code and dataset will be publicly released upon acceptance.

cs.CV↗

arXiv2025

DistillFSS: Synthesizing Few-Shot Knowledge into a Lightweight Segmentation Model

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: source and target domains exhibit substantial distribution shifts, label spaces are disjoint, and support images are scarce--making standard episodic methods unreliable and computationally demanding at test time. To address these constraints, we propose DistillFSS, a framework that embeds support-set knowledge directly into a model's parameters through a teacher--student distillation process. By internalizing few-shot reasoning into a dedicated layer within the student network, DistillFSS eliminates the need for support images at test time, enabling fast, lightweight inference, while allowing efficient extension to novel classes in unseen domains through rapid teacher-driven specialization. Combined with fine-tuning, the approach scales efficiently to large support sets and significantly reduces computational overhead. To evaluate the framework under realistic conditions, we introduce a new CD-FSS benchmark spanning medical imaging, industrial inspection, and remote sensing, with disjoint label spaces and variable support sizes. Experiments show that DistillFSS matches or surpasses state-of-the-art baselines, particularly in multi-class and multi-shot scenarios, while offering substantial efficiency gains. The code is available at https://github.com/pasqualedem/DistillFSS.

cs.CV↗

arXiv2025

Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design

Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. While explainable AI has advanced significantly in standard computer vision tasks, interpretability in FSS remains virtually unexplored despite its critical importance for understanding model behavior and guiding support set selection in data-scarce scenarios. This paper introduces the first dedicated method for interpreting matching-based FSS models by leveraging their inherent structural properties. Our Affinity Explainer approach extracts attribution maps that highlight which pixels in support images contribute most to query segmentation predictions, using matching scores computed between support and query features at multiple feature levels. We extend standard interpretability evaluation metrics to the FSS domain and propose additional metrics to better capture the practical utility of explanations in few-shot scenarios. Comprehensive experiments on FSS benchmark datasets, using different models, demonstrate that our Affinity Explainer significantly outperforms adapted standard attribution methods. Qualitative analysis reveals that our explanations provide structured, coherent attention patterns that align with model architectures and and enable effective model diagnosis. This work establishes the foundation for interpretable FSS research, enabling better model understanding and diagnostic for more reliable few-shot segmentation systems. The source code is publicly available at https://github.com/pasqualedem/AffinityExplainer.

cs.CV↗

arXiv2025

Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Prompts

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 novel transformer-based architecture designed for multi-prompt, multi-way few-shot semantic segmentation. Our approach leverages diverse visual prompts -- points, bounding boxes, and masks -- to create a highly flexible and generalizable framework that significantly reduces annotation burden while maintaining high accuracy. Label Anything makes three key contributions: ($\textit{i}$) we introduce a new task formulation that relaxes conventional few-shot segmentation constraints by supporting various types of prompts, multi-class classification, and enabling multiple prompts within a single image; ($\textit{ii}$) we propose a novel architecture based on transformers and attention mechanisms; and ($\textit{iii}$) we design a versatile training procedure allowing our model to operate seamlessly across different $N$-way $K$-shot and prompt-type configurations with a single trained model. Our extensive experimental evaluation on the widely used COCO-$20^i$ benchmark demonstrates that Label Anything achieves state-of-the-art performance among existing multi-way few-shot segmentation methods, while significantly outperforming leading single-class models when evaluated in multi-class settings. Code and trained models are available at https://github.com/pasqualedem/LabelAnything.

cs.CV↗

arXiv2025

ArtSeek: Deep artwork understanding via multimodal in-context reasoning and late interaction retrieval

Analyzing digitized artworks presents unique challenges, requiring not only visual interpretation but also a deep understanding of rich artistic, contextual, and historical knowledge. We introduce ArtSeek, a multimodal framework for art analysis that combines multimodal large language models with retrieval-augmented generation. Unlike prior work, our pipeline relies only on image input, enabling applicability to artworks without links to Wikidata or Wikipedia-common in most digitized collections. ArtSeek integrates three key components: an intelligent multimodal retrieval module based on late interaction retrieval, a contrastive multitask classification network for predicting artist, genre, style, media, and tags, and an agentic reasoning strategy enabled through in-context examples for complex visual question answering and artwork explanation via Qwen2.5-VL. Central to this approach is WikiFragments, a Wikipedia-scale dataset of image-text fragments curated to support knowledge-grounded multimodal reasoning. Our framework achieves state-of-the-art results on multiple benchmarks, including a +8.4% F1 improvement in style classification over GraphCLIP and a +7.1 BLEU@1 gain in captioning on ArtPedia. Qualitative analyses show that ArtSeek can interpret visual motifs, infer historical context, and retrieve relevant knowledge, even for obscure works. Though focused on visual arts, our approach generalizes to other domains requiring external knowledge, supporting scalable multimodal AI research. Both the dataset and the source code will be made publicly available at https://github.com/cilabuniba/artseek.

cs.CV↗

arXiv2024

I Dream My Painting: Connecting MLLMs and Diffusion Models via Prompt Generation for Text-Guided Multi-Mask Inpainting

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 effective for text-guided inpainting, we introduce the novel task of multi-mask inpainting, where multiple regions are simultaneously inpainted using distinct prompts. Furthermore, we design a fine-tuning procedure for multimodal LLMs, such as LLaVA, to generate multi-mask prompts automatically using corrupted images as inputs. These models can generate helpful and detailed prompt suggestions for filling the masked regions. The generated prompts are then fed to Stable Diffusion, which is fine-tuned for the multi-mask inpainting problem using rectified cross-attention, enforcing prompts onto their designated regions for filling. Experiments on digitized paintings from WikiArt and the Densely Captioned Images dataset demonstrate that our pipeline delivers creative and accurate inpainting results. Our code, data, and trained models are available at https://cilabuniba.github.io/i-dream-my-painting.

cs.CV↗

arXiv2024

Neural network modelling of kinematic and dynamic features for signature verification

Online signature parameters, which are based on human characteristics, broaden the applicability of an automatic signature verifier. Although kinematic and dynamic features have previously been suggested, accurately measuring features such as arm and forearm torques remains challenging. We present two approaches for estimating angular velocities, angular positions, and force torques. The first approach involves using a physical UR5e robotic arm to reproduce a signature while capturing those parameters over time. The second method, a cost effective approach, uses a neural network to estimate the same parameters. Our findings demonstrate that a simple neural network model can extract effective parameters for signature verification. Training the neural network with the MCYT300 dataset and cross validating with other databases, namely, BiosecurID, Visual, Blind, OnOffSigDevanagari 75 and OnOffSigBengali 75 confirm the models generalization capability.

cs.LG↗

arXiv2024

RoWeeder: Unsupervised Weed Mapping through Crop-Row Detection

Precision agriculture relies heavily on effective weed management to ensure robust crop yields. This study presents RoWeeder, an innovative framework for unsupervised weed mapping that combines crop-row detection with a noise-resilient deep learning model. By leveraging crop-row information to create a pseudo-ground truth, our method trains a lightweight deep learning model capable of distinguishing between crops and weeds, even in the presence of noisy data. Evaluated on the WeedMap dataset, RoWeeder achieves an F1 score of 75.3, outperforming several baselines. Comprehensive ablation studies further validated the model's performance. By integrating RoWeeder with drone technology, farmers can conduct real-time aerial surveys, enabling precise weed management across large fields. The code is available at: \url{https://github.com/pasqualedem/RoWeeder}.

cs.CV↗

arXiv2024

Art2Mus: Bridging Visual Arts and Music through Cross-Modal Generation

Artificial Intelligence and generative models have revolutionized music creation, with many models leveraging textual or visual prompts for guidance. However, existing image-to-music models are limited to simple images, lacking the capability to generate music from complex digitized artworks. To address this gap, we introduce $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$, a novel model designed to create music from digitized artworks or text inputs. $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$ extends the AudioLDM~2 architecture, a text-to-audio model, and employs our newly curated datasets, created via ImageBind, which pair digitized artworks with music. Experimental results demonstrate that $\mathcal{A}\textit{rt2}\mathcal{M}\textit{us}$ can generate music that resonates with the input stimuli. These findings suggest promising applications in multimedia art, interactive installations, and AI-driven creative tools.

cs.MM↗

arXiv2023

Density-based clustering with fully-convolutional networks for crowd flow detection from drones

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 a solution to crowd flow detection is still an unexplored research question. To this end, we propose a crowd flow detection method for video sequences shot by a drone. The method is based on a fully-convolutional network that learns to perform crowd clustering in order to detect the centroids of crowd-dense areas and track their movement in consecutive frames. The proposed method proved effective and efficient when tested on the Crowd Counting datasets of the VisDrone challenge, characterized by video sequences rather than still images. The encouraging results show that the proposed method could open up new ways of analyzing high-level crowd behavior from drones.

cs.CV↗

arXiv2022

A deep learning approach to clustering visual arts

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 other hand, applying traditional clustering and feature reduction techniques to the highly dimensional pixel space can be ineffective. To address these issues, in this paper we propose DELIUS: a DEep learning approach to cLustering vIsUal artS. The method uses a pre-trained convolutional network to extract features and then feeds these features into a deep embedded clustering model, where the task of mapping the input data to a latent space is jointly optimized with the task of finding a set of cluster centroids in this latent space. Quantitative and qualitative experimental results show the effectiveness of the proposed method. DELIUS can be useful for several tasks related to art analysis, in particular visual link retrieval and historical knowledge discovery in painting datasets.

cs.CV↗

arXiv2021

Integrating Contextual Knowledge to Visual Features for Fine Art Classification

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 digitized artwork images, sometimes supplemented with some metadata and textual comments. A knowledge graph that integrates a rich body of information about artworks, artists, painting schools, etc., in a unified structured framework can provide a valuable resource for more powerful information retrieval and knowledge discovery tools in the artistic domain. To this end, this paper presents ArtGraph: an artistic knowledge graph based on WikiArt and DBpedia. The graph, implemented in Neo4j, already provides knowledge discovery capabilities without having to train a learning system. In addition, the embeddings extracted from the graph are used to inject "contextual" knowledge into a deep learning model to improve the accuracy of artwork attribute prediction tasks.

cs.CV↗

arXiv2021

VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results

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. However, there are few algorithms focusing on crowd counting on the drone-captured data due to the lack of comprehensive datasets. To this end, we collect a large-scale dataset and organize the Vision Meets Drone Crowd Counting Challenge (VisDrone-CC2020) in conjunction with the 16th European Conference on Computer Vision (ECCV 2020) to promote the developments in the related fields. The collected dataset is formed by $3,360$ images, including $2,460$ images for training, and $900$ images for testing. Specifically, we manually annotate persons with points in each video frame. There are $14$ algorithms from $15$ institutes submitted to the VisDrone-CC2020 Challenge. We provide a detailed analysis of the evaluation results and conclude the challenge. More information can be found at the website: \url{http://www.aiskyeye.com/}.

cs.CV↗