Marco Fiorucci
Post Doc
Postdoctoral Researcher in Machine Learning
About
Marco Fiorucci is a postdoctoral researcher in Machine Learning at the Center for Cultural Heritage Technology (CCHT@CaFoscari) of the Istituto Italiano di Tecnologia (IIT) since 2019, working on the development of next-generation Machine Learning approaches applied to the Cultural Heritage. He is working mainly in the fields of Machine Learning and Pattern Recognition, with particular emphasis on geometric deep learning methods and on graph generative models. Marco received his PhD in Computer Science from Ca’ Foscari University of Venice in 2019. His PhD thesis proposes a robust graph summarization method based on Szemerédi’s Regularity Lemma and discusses its relevance in the context of Structural Pattern Recognition. He held visiting research position at University of Alicante and at VTT (Finland). Previously, he graduated summa cum laude in Computer Science at Ca’ Foscari University of Venice in 2015. In addition to research, Marco is one of the co-founder and co-organizer of DataBeersVenezia and one of the communication managers of the CCHT.
Interests
Machine Learning Pattern Recognition Learning Theory Cultural HeritageIIT Publications
- 2020
-
Ancient Document Layout Analysis: Autoencoders meet Sparse Coding
25th International Conference on Pattern Recognition -
DOI
Machine Learning for Cultural Heritage: A Survey
Pattern Recognition Letters, vol. 133, pp. 102-108 -
Semi-supervised classification of ancient coins using graph neural networks
Conference on Computer Applications and Quantitative Methods in Archaeology (CAA) -
DOI
Separating Structure from Noise in Large Graphs Using the Regularity Lemma
Pattern Recognition, vol. 98 - 2019
-
DOI
Analysis of large sparse graphs using regular decomposition of graph distance matrices
Proceedings - 2018 IEEE International Conference on Big Data, Big Data 2018, pp. 3784-3792 -
Graph Convolutional Neural Networks for Cultural Heritage: Applications in RS recognition, numismatics and epigraphy
Machine Learning in Archaeology, Rome - 2018
-
Graph Summarization Using Regular Partitions
The 8th International Conference on Network Analysis, Moscow - 2017
-
DOI
A computer vision system for the automatic inventory of a cooler
Lecture Notes in Computer Science, vol. 10484 LNCS, pp. 575-585 -
DOI
On the interplay between strong regularity and graph densification
Lecture Notes in Computer Science, vol. 10310 LNCS, pp. 165-174 -
DOI
Revealing structure in large graphs: Szemerédi's regularity lemma and its use in pattern recognition
Pattern Recognition Letters, vol. 87, pp. 4-11 - 2015
-
DOI
Exploring the organisation of complex systems through the dynamical interactions among their relevant subsets
European Conference of Artificial Life -
DOI
The search for candidate relevant subsets of variables in complex systems
Artificial Life, vol. 21, (no. 4), pp. 412-431 - 2014
-
Dynamical Cluster Index: advances and new results.
European Conference of Complex Systems -
DOI
On some properties of information theoretical measures for the study of complex systems
Communications in Computer and Information Science, vol. 445, pp. 140-150
Dissemination Talks
- 2019
-
L'intelligenza artificiale a servizio dell'arte
Scientific Talks
- 2019
-
Graph Convolutional Neural Networks for Cultural Heritage: Applications in RS recognition, numismatics and epigraphy
- 2018
-
Graph Summarization Using Regular Partitions