Search

Your search keyword '"Fantozzi, Carlo"' showing total 40 results
Start Over Author "Fantozzi, Carlo"
40 results on '"Fantozzi, Carlo"'

3. Clustering Uncertain Graphs

Author

Ceccarello, Matteo, Fantozzi, Carlo, Pietracaprina, Andrea, Pucci, Geppino, and Vandin, Fabio

Subjects
Computer Science - Data Structures and Algorithms
Abstract

An uncertain graph $\mathcal{G} = (V, E, p : E \rightarrow (0,1])$ can be viewed as a probability space whose outcomes (referred to as \emph{possible worlds}) are subgraphs of $\mathcal{G}$ where any edge $e\in E$ occurs with probability $p(e)$, independently of the other edges. These graphs naturally arise in many application domains where data management systems are required to cope with uncertainty in interrelated data, such as computational biology, social network analysis, network reliability, and privacy enforcement, among the others. For this reason, it is important to devise fundamental querying and mining primitives for uncertain graphs. This paper contributes to this endeavor with the development of novel strategies for clustering uncertain graphs. Specifically, given an uncertain graph $\mathcal{G}$ and an integer $k$, we aim at partitioning its nodes into $k$ clusters, each featuring a distinguished center node, so to maximize the minimum/average connection probability of any node to its cluster's center, in a random possible world. We assess the NP-hardness of maximizing the minimum connection probability, even in the presence of an oracle for the connection probabilities, and develop efficient approximation algorithms for both problems and some useful variants. Unlike previous works in the literature, our algorithms feature provable approximation guarantees and are capable to keep the granularity of the returned clustering under control. Our theoretical findings are complemented with several experiments that compare our algorithms against some relevant competitors, with respect to both running-time and quality of the returned clusterings.

Published
2016

9. Improving Existing Segmentators Performance with Zero-Shot Segmentators.

Author

Nanni, Loris, Fusaro, Daniel, Fantozzi, Carlo, and Pretto, Alberto

Subjects
TRAINING needs, DEEP learning
Abstract

This paper explores the potential of using the SAM (Segment-Anything Model) segmentator to enhance the segmentation capability of known methods. SAM is a promptable segmentation system that offers zero-shot generalization to unfamiliar objects and images, eliminating the need for additional training. The open-source nature of SAM allows for easy access and implementation. In our experiments, we aim to improve the segmentation performance by providing SAM with checkpoints extracted from the masks produced by mainstream segmentators, and then merging the segmentation masks provided by these two networks. We examine the "oracle" method (as upper bound baseline performance), where segmentation masks are inferred only by SAM with checkpoints extracted from the ground truth. One of the main contributions of this work is the combination (fusion) of the logit segmentation masks produced by the SAM model with the ones provided by specialized segmentation models such as DeepLabv3+ and PVTv2. This combination allows for a consistent improvement in segmentation performance in most of the tested datasets. We exhaustively tested our approach on seven heterogeneous public datasets, obtaining state-of-the-art results in two of them (CAMO and Butterfly) with respect to the current best-performing method with a combination of an ensemble of mainstream segmentator transformers and the SAM segmentator. The results of our study provide valuable insights into the potential of incorporating the SAM segmentator into existing segmentation techniques. We release with this paper the open-source implementation of our method. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

15. At Home With Us

Author

Fantozzi, Carlo, primary, Grigoletto, Lorenzo, additional, and Pasquato, Marco, additional

Published
2020
Full Text
View/download PDF

22. Listen By Looking

Author

Pitteri, Giulio, primary, Micheloni, Edoardo, additional, Rodà, Antonio, additional, Fantozzi, Carlo, additional, and Orio, Nicola, additional

Published
2019
Full Text
View/download PDF

25. Clustering uncertain graphs

Author

Ceccarello, Matteo, primary, Fantozzi, Carlo, additional, Pietracaprina, Andrea, additional, Pucci, Geppino, additional, and Vandin, Fabio, additional

Published
2017
Full Text
View/download PDF

31. AuroraScience Project. Report on the First Phase

Author

Beccara, S., Alfieri, R., Artico, Fausto, Bilardi, Gianfranco, Brambilla, M., Bogo, Federica, Cappelleri, VINCENZO MARIA, Cestaro, A., Cilia, E., Cristoforetti, M., Dalla Brida, M., D'Antonio, M., Di Renzo, F., Destri, C., Faccioli, P., Fantozzi, Carlo, Fontana, P., Gargano, G., Grossi, M., Illarionov, A. Y., Leonardi, R., Leidemann, W., Marchesini, G., Milani, Emanuele, Moser, C., Onofri, E., Orlandini, G., Pederiva, F., Peruch, Francesco, PESERICO STECCHINI NEGRI DE SALVI, Enoch, Pietracaprina, ANDREA ALBERTO, Pivanti, M., Pozzati, F., Pucci, Geppino, Rapuano, F., Richter, A., Sega, M., Schifano, S. F., Schimd, Michele, Schwarz, M., Scorzato, L., Simma, H., Skrbica, T., Tagliavini, E., Traini, M., Tripiccione, R., Velasco, R., Verrocchio, P., Versaci, Francesco, Yuan, L., and Zago, Nicola

Published
2012

40. RPM-android: a tablet application to cooperate with vulnerable families

Author

Carlo Fantozzi, Marco Ius, Sara Serbati, Zanon, Ombretta, Milani, Paola, Fantozzi, Carlo, Ius, Marco, Serbati, Sara, Zanon, Ombretta, Milani, Paola, Ionescu S., Tomita M.,Cace S., Fantozzi, C, Ius, M, Serbati, S, Zanon, O, and Milani, P

Subjects
vulnerable families, tablet app, resilience based tool, vulnerable familie
Abstract

One of the main questions professionals raise in meetings and training is to have new tools useful to connect theories and practice and to facilitate and support their complex work with families. Within P.I.P.P.I. (Intervention Program for Prevention of Institutionalization), particular focus is placed on tools supporting intervention process within a participatory and transformative evaluation perspective where linking assessment, planning, intervention and evaluation is key. PIPPIapp is an Android tablet application developed in collaboration with DEI (Department of Information Engineering) that aims at providing professionals with a tool that is user-friendly for them and their relational work with children and parents, and that facilitates the simultaneous use of the main functions of the web-tool RPM developed in collaboration with the CSIA (Information Technology Center) of the University. PIPPIapp is based on the Italian adaptation of the triangular model of the British Common Assessment Framework and it is designed to: • access to “the triangle” of each child through a safe log in; • foster the “story telling” process of children and parents within a resilience based approach; • support and facilitate the work with families in assessment, planning and evaluation; • easily document practice (microplanning, evaluating results and recording the journal of meetings with family); • record data off line in the tablet memory and upload data on RPMdatabase when online; • collect Eco-maps of children and parents through the function “mAPPamondo”; • share data with the family members and other professionals working with them; • use data for research and to improve practice by reflective meetings. After showing the app, how it works and its use with children and families, the presentation will focus on the data and feedback about the experimentation of its first implementation (sep. 2013 – apr. 2014) within the PIPPI program with a group of 10 professionals working with 10 families.

Published
2014

Catalog

Books, media, physical & digital resources
See catalog results