Dottorato in Ingegneria Elettrica, Elettronica E Delle Comunicazioni , 36o ciclo (2020-2023)
Dottorato concluso nel 2024
Tesi:
Exploring the latent geometry for representation learning (Abstract)
Tutori:
Enrico Magli Diego ValsesiaProfilo
Argomento di ricerca
Remote sensing image processing using machine learning and deep learning techniques.
Interessi di ricerca
Biografia
I got my bachelor and master degree from Università di Torino in physics in 2018 and 2020 respectively.
My first experience in the world of research started during my bachelor thesis, at Astronomical observatory INAF of Pino Torinese (TO). Here I adapted an old simulator to the purpose of detecting strange quark matter (nuclearites) from the Russian detector TUS.
During the master degree in theoretical physics, I worked for master thesis in machine learning for space images processing. During this period I have collaborated with Riken, an international research center in Japan where I have been for two months. A lot of work was done trying to apply recent neural networks models to data of Mini-EUSO, a detector mounting on ISS able to detect cosmic rays, space debris, transient luminous events and other events.
The exciting and promising results led me to decide this research area as my future research. Then I chose Politecnico di Torino for proceeding my career and do my best within the research group of prof. E.Magli for remote sensing image processing developing advanced and sophisticated deep learning techniques.
Didattica
Insegnamenti
Corso di laurea magistrale
- Methods and tools for ICT. A.A. 2022/23, ICT FOR SMART SOCIETIES (ICT PER LA SOCIETA' DEL FUTURO). Collaboratore del corso
- Methods and tools for ICT. A.A. 2023/24, ICT FOR SMART SOCIETIES (ICT PER LA SOCIETA' DEL FUTURO). Collaboratore del corso
- Signal, image and video processing and learning (modulo di Image and video processing and learning). A.A. 2022/23, COMMUNICATIONS ENGINEERING. Collaboratore del corso
- Signal, image and video processing and learning (modulo di Image and video processing and learning). A.A. 2023/24, COMMUNICATIONS ENGINEERING. Collaboratore del corso
Pubblicazioni
Pubblicazioni durante il dottorato Vedi tutte le pubblicazioni su Porto@Iris
- Montanaro, A.; SAVANT AIRA, Luca; Aiello, E.; Valsesia, D.; Magli, E. (2024)
MOTIONCRAFT: Physics-based Zero-Shot Video Generation. In: 38th Conference on Neural Information Processing Systems, NeurIPS 2024, Vancouver (Can), 10 - 15 December 2024. ISSN 1049-5258
Contributo in Atti di Convegno (Proceeding) - Montanaro, Antonio (2024)
Exploring the latent geometry for representation learning. relatore: MAGLI, ENRICO; VALSESIA, DIEGO; , 36. XXXVI Ciclo, P.: 147
Doctoral Thesis - Montanaro, Antonio; Valsesia, Diego; Magli, Enrico (2023)
Towards Hyperbolic Regularizers For Point Cloud Part Segmentation. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 04-10 June 2023, pp. 1-5. ISBN: 978-1-7281-6327-7
Contributo in Atti di Convegno (Proceeding) - Montanaro, Antonio; Valsesia, Diego; Magli, Enrico (2022)
Exploring the Solution Space of Linear Inverse Problems with GAN Latent Geometry. In: 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France, 16-19 October 2022, pp. 1381-1385. ISBN: 978-1-6654-9620-9
Contributo in Atti di Convegno (Proceeding) - Montanaro, A.; Ebisuzaki, T.; Bertaina, M. (2022)
Stack-CNN algorithm: A new approach for the detection of space objects. In: JOURNAL OF SPACE SAFETY ENGINEERING, vol. 9, pp. 72-82. ISSN 2468-8967
Contributo su Rivista - Montanaro, A.; Valsesia, D.; Magli, E. (2022)
Rethinking the compositionality of point clouds through regularization in the hyperbolic space. In: 36th Conference on Neural Information Processing Systems, NeurIPS 2022, New Orleans, USA, November 28th through December 9th, 2022. ISSN 1049-5258. ISBN: 9781713871088
Contributo in Atti di Convegno (Proceeding)