Marco Fiorucci is an Experienced Researcher Marie Curie in Machine Learning at the Centre for Cultural Heritage Technology (CCHT) of the Istituto Italiano di Tecnologia (IIT). He is working mainly in the field of Machine Learning, with particular emphasis on optimal transport. In this context, Marco has won a MSCA-IF for his OPTIMAL project that aims to develop an efficient and principled Machine Learning approach based on Optimal Transport to automatically detect looting (past and present) directly on airborne LiDAR point cloud time-series. He is a computer scientist with a solid broad background, spanning from Physics and Machine Learning to Graph Theory and Statistics. He has successfully worked on several different interdisciplinary projects in academia and in industry. He received the Master degree (summa cum laude) and his PhD in Computer Science from Ca’ Foscari University of Venice respectively in 2015 and 2019. He held visiting research position at the University of Alicante and at VTT (Finland). More recently, he has shifted his attention to the analysis of EO data (multispectral and hyperspectral data) and airborne LiDAR for detecting sub-surface archaeological sites (ESA-CLS). 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.
Phone
+39 041 2346757
Address
Campus Scientifico Ca' Foscari Edificio Epsilon Via Torino, 155 30170 - Mestre (VE)
Research center
CCHT@Ca'Foscari Venezia
About
All Publications
2024
Naylor P., Di Carlo D., Traviglia A., Yamada M., Fiorucci M.
Implicit Neural Representation for Change Detection
2024 IEEE Winter Conference on Applications of Computer Vision, WACV 2024
Conference Paper
Conference
2023
Fiorucci M., Naylor P., Yamada M.
Optimal Transport for Change Detection on LiDAR Point Clouds
Digest - International Geoscience and Remote Sensing Symposium (IGARSS)
Conference Paper
Conference
2023
Sech G., Soleni P., Verschoof-van der Vaart B., Kokalj Z., Traviglia A., Fiorucci M.
Transfer Learning of Semantic Segmentation Methods for Identifying Buried Archaeological Structures On LiDAR Data
Digest - International Geoscience and Remote Sensing Symposium (IGARSS)
Conference Paper
Conference
2022
Fiorucci M., Verschoof-Van der Vaart W.B., Soleni P., Saux B.L., Traviglia A.
Deep Learning for Archaeological Object Detection on LiDAR: New Evaluation Measures and Insights
Remote Sensing, vol. 14, (no. 7)
2020
Traviglia A., Artesani A., Fiorucci M., Ljubenovic M.
Advances in Hyperspectral Data Processing for Cultural Heritage
European Physical Journal Plus
Editorial
Journal
Dissemination
2019
Fiorucci M.
L'intelligenza artificiale a servizio dell'arte
Databeers Venezia
Public Event
Scientific Talks
2023
Fiorucci M.
Implicit Learning for Unsupervised Change Detection
Kyoto University
Institute
2023
Fiorucci M.
OPtimal Transport for Identifying Marauder Activities on Lidar
Okinawa Institute of Technology (Okinawa, Japan)
Institute
2023
Fiorucci M.
Scalable Unbalanced Optimal Transport for Change Detection
The Institute of Statistical Mathematics, Tokyo
Institute
2023
Fiorucci M.
Unbalanced Optimal Transport for Change Detection
Osaka University
Institute
2018
Fiorucci M.
Graph Summarization Using Regular Partition and Its Use in Graph Search
Department of Mathematics and Systems Analysis, Aalto University
Institute
Oral presentations
2023
Fiorucci M., Naylor P., Yamada M.
Optimal Transport for Change Detection on LiDAR Point Clouds
Digest - International Geoscience and Remote Sensing Symposium (IGARSS)
Conference
2019
Traviglia A., Fiorucci M.
Graph Convolutional Neural Networks for Cultural Heritage: Applications in RS recognition, numismatics and epigraphy
Machine Learning in Archaeology, Rome
Conference
2018
Pelosin F., Fiorucci M., and Pelillo M.
Graph Summarization Using Regular Partitions
The 8th International Conference on Network Analysis, Moscow
Conference
Editorships
2020-2021
Traviglia A., Artesani A., Fiorucci M., Ljubenovic M.
European Physical Journal Plus
Colleagues of Cultural Heritage Technologies