Publications

Styled Handwritten Text Generation (HTG) has received significant attention in recent years,propelled by the success of learning-based solutions employing GANs,Transformers,and,preliminarily,Diffusion Models. Despite this surge in interest,there remains a critical yet understudied aspect - the impact of the input,both visual and textual,on the HTG model training and its subsequent influence on performance. This work extends the VATr [1] Styled-HTG approach by addressing the pre-processing and training issues that it faces,which are common to many HTG models. In particular,we propose generally applicable strategies for input preparation and training regularization that allow the model to achieve better performance and generalization capabilities. Moreover,in this work,we go beyond performance optimization and address a significant hurdle in HTG research - the lack of a standardized evaluation protocol. In particular,we propose a standardization of the evaluation protocol for HTG and conduct a comprehensive benchmarking of existing approaches. By doing so,we aim to establish a foundation for fair and meaningful comparisons between HTG strategies,fostering progress in the field.

Regesta are catalogs of summaries of other documents and, in some cases, are the only source of information about the content of such full-length documents. For this reason, they are of great interest to scholars in many social and humanities fields. In this work, we focus on Regesta Pontificum Romanum, a large collection of papal registers. Regesta are visually rich documents, where the layout is as important as the text content to convey the contained information through the structure, and are inherently multi-page documents. Among Digital Humanities techniques that can help scholars efficiently exploit regesta and other documental sources in the form of scanned documents, Document Parsing has emerged as a task to process document images and convert them into machine-readable structured representations, usually markup language. However, current models focus on scientific and business documents, and most of them consider only single-paged documents. To overcome this limitation, in this work, we propose μgat, an extension of the recently proposed Document parsing Nougat architecture, which can handle elements spanning over the single page limits. Specifically, we adapt Nougat to process a larger, multi-page context, consisting of the previous and the following page, while parsing the current page. Experimental results, both qualitative and quantitative, demonstrate the effectiveness of our proposed approach also in the case of the challenging Regesta Pontificum Romanorum.

Diffusion-based Handwritten Text Generation (HTG) approaches achieve impressive results on frequent, invocabulary words observed at training time and on regular styles. However, they are prone to memorizing training samples and often struggle with style variability and generation clarity. In particular, standard diffusion models tend to produce artifacts or distortions that negatively affect the readability of the generated text, especially when the style is hard to produce. To tackle these issues, we propose a novel sampling guidance strategy, Dual Orthogonal Guidance (DOG), that leverages an orthogonal projection of a negatively perturbed prompt onto the original positive prompt. This approach helps steer the generation away from artifacts while maintaining the intended content, and encourages more diverse, yet plausible, outputs. Unlike standard Classifier-Free Guidance (CFG), which relies on unconditional predictions and produces noise at high guidance scales, DOG introduces a more stable, disentangled direction in the latent space. To control the strength of the guidance across the denoising process, we apply a triangular schedule: weak at the start and end of denoising, when the process is most sensitive, and strongest in the middle steps. Experimental results on the state-of-the-art DiffusionPen and One-DM demonstrate that DOG improves both content clarity and style variability, even for out-of-vocabulary words and challenging writing styles.

QR and Datamatrix codes are widely used in warehouse logistics and high-speed production pipelines. Still, distant or small barcodes often yield low-pixel-density images that are hard to read. Conventional solutions rely on costly hardware or enhanced lighting, raising expenses and potentially reducing depth of field. We propose Mosaic-SR, a multi-step, adaptive super-resolution (SR) method that devotes more computation to barcode regions than uniform backgrounds. For each patch, it predicts an uncertainty value to decide how many refinement steps are required. Our experiments show that Mosaic-SR surpasses state-of-the-art SR models on 2D barcode images, achieving higher PSNR and decoding rates in less time. All code and trained models are publicly available at https://github.com/Henvezz95/mosaic-sr.

We introduce Sanctuaria-Gaze, a multimodal dataset featuring egocentric recordings from 40 visits to four architecturally and culturally significant sanctuaries in Northern Italy. Collected using wearable devices with integrated eye trackers, the dataset offers RGB videos synchronized with streams of gaze coordinates, head motion, and environmental point cloud, resulting in over four hours of recordings. Along with the dataset, we provide a framework for automatic detection and analysis of Areas of Interest (AOIs). This framework fills a critical gap by offering an open-source, flexible tool for gaze-based research that adapts to dynamic settings without requiring manual intervention. Our study analyzes human visual attention to sacred, architectural, and cultural objects, providing insights into how visitors engage with these elements and how their background influences their interactions. By releasing both the dataset and the analysis framework, Sanctuaria-Gaze aims to advance interdisciplinary research on gaze behavior, human-computer interaction, and visual attention in real-world environments. Code and dataset are available at https://github.com/aimagelab/Sanctuaria-Gaze.

Drawing analogies between two pairs of entities in the form of A:B::C:D (i.e. A is to B as C is to D) is a hallmark of human intelligence, as evidenced by sufficient findings in cognitive science for the last decades. In recent years, this property has been found far beyond cognitive science. Notable examples are word2vec and GloVe models in natural language processing. Recent research in computer vision also found the property of analogies in the feature space of a pretrained ConvNet feature extractor. However, analogy mining in the semantic space of recent strong foundation models such as CLIP is still understudied, despite the fact that they have been successfully applied to a wide range of downstream tasks. In this work, we show that CLIP possesses the similar ability of analogical reasoning in the latent space, and propose a novel strategy to extract analogies between pairs of images in the CLIP space. We compute all the difference vectors of a pair of any two images that belong to the same class in the CLIP space, and employ k-means clustering to group the difference vectors into clusters irrespective of their classes. This procedure results in cluster centroids representative of class-agnostic semantic analogies between images. Through extensive analysis, we show that the property of drawing analogies between images also exists in the CLIP space, which are interpretable by humans through a visualisation of the learned clusters.

The control of soil-borne diseases in hops, such as Verticillium wilt remains challenging due to the limited effectiveness of fungicides, the perennial nature of hop cultivation, and the long-term persistence of the pathogens in the soil. Microbial biocontrol agents (mBCAs) with plant growth-promoting (PGP) and antagonistic effects offer a sustainable ecofriendly alternative for hops protection. Two Pseudomonas spp. strains from the UniMORE microbial collection were selected for this study based on their strong antagonistic activity against Verticillium spp. and multiple plant growth-promoting (PGP) traits. Rhizospheric and endophytic colonization capacities of the strains DLS1929 and DLS2318 were evaluated in hop plants (cv. Cascade) under controlled conditions at seven- and fourteen-days post-inoculation (DPI). Both bacterial strains were rhizosphere and endorhiza competent, with slight differences in their abundances. The highest cell density was observed at 7 DPI for the strain DLS2318, reaching log10 6.39 CFU g−1 root fresh weight in the rhizosphere and log10 4.75 CFU g−1 root fresh weight in the endorhiza; at 14 DPI, colonization results were in line with the previous assessment. Confocal laser scanning microscopy visualization of both eGFP-tagged Pseudomonas spp. strains confirmed their rhizosphere competence in hop. Additionally, root colonization by these bacteria enhanced the photosynthetic capacity in hop leaves, supporting their potential as a PGP agents observed in vitro. Successful root colonization and PGP effects are key prerequisites for an effective biocontrol of soilborne pathogens. Further studies are required to assess the consistent efficacy in the field of these beneficial mBCA candidates. This research was funded by the Italian Ministry of University and Research (MUR), under the European Union funding – Next Generation EU - PRIN- 2022, (prot. 2022M3HR45) project: “IoHOP: Quality valorization of the Italian hop based on a multi-approach strategy”.

Image captioning has attracted significant attention within the Computer Vision and Multimedia research domains, resulting in the development of effective methods for generating natural language descriptions of images. Concurrently, the rise of generative models has facilitated the production of highly realistic and high-quality images, particularly through recent advancements in latent diffusion models. In this paper, we propose to leverage the recent advances in Generative AI and create additional training data that can be effectively used to boost the performance of an image captioning model. Specifically, we combine real images with their synthetic counterparts generated by Stable Diffusion using a Mixup data augmentation technique to create novel training examples. Extensive experiments on the COCO dataset demonstrate the effectiveness of our solution in comparison to different baselines and state-of-the-art methods and validate the benefits of using synthetic data to augment the training stage of an image captioning model and improve the quality of the generated captions. Source code and trained models are publicly available at: https://github.com/aimagelab/synthcap_pp.