Zobrazeno 1 - 10
of 120
pro vyhledávání: '"G, Turrisi"'
Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. A recent research direction for improving few-shot classifiers involves augmenting the labelled samples with synthetic images create
Externí odkaz:
http://arxiv.org/abs/2312.03046
Autor:
da Costa, Victor G. Turrisi, Zara, Giacomo, Rota, Paolo, Oliveira-Santos, Thiago, Sebe, Nicu, Murino, Vittorio, Ricci, Elisa
Over the last few years, Unsupervised Domain Adaptation (UDA) techniques have acquired remarkable importance and popularity in computer vision. However, when compared to the extensive literature available for images, the field of videos is still rela
Externí odkaz:
http://arxiv.org/abs/2207.12842
Autor:
Fini, Enrico, da Costa, Victor G. Turrisi, Alameda-Pineda, Xavier, Ricci, Elisa, Alahari, Karteek, Mairal, Julien
Self-supervised models have been shown to produce comparable or better visual representations than their supervised counterparts when trained offline on unlabeled data at scale. However, their efficacy is catastrophically reduced in a Continual Learn
Externí odkaz:
http://arxiv.org/abs/2112.04215
This paper presents solo-learn, a library of self-supervised methods for visual representation learning. Implemented in Python, using Pytorch and Pytorch lightning, the library fits both research and industry needs by featuring distributed training p
Externí odkaz:
http://arxiv.org/abs/2108.01775
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
da Costa, Victor G. Turrisi, Mastelini, Saulo Martiello, de Carvalho, André C. Ponce de Leon Ferreira, Barbon Jr, Sylvio
As more data are produced each day, and faster, data stream mining is growing in importance, making clear the need for algorithms able to fast process these data. Data stream mining algorithms are meant to be solutions to extract knowledge online, sp
Externí odkaz:
http://arxiv.org/abs/1907.07207
Autor:
G. Coppini, P. Marra, R. Lecci, N. Pinardi, S. Cretì, M. Scalas, L. Tedesco, A. D'Anca, L. Fazioli, A. Olita, G. Turrisi, C. Palazzo, G. Aloisio, S. Fiore, A. Bonaduce, Y. V. Kumkar, S. A. Ciliberti, I. Federico, G. Mannarini, P. Agostini, R. Bonarelli, S. Martinelli, G. Verri, L. Lusito, D. Rollo, A. Cavallo, A. Tumolo, T. Monacizzo, M. Spagnulo, R. Sorgente, A. Cucco, G. Quattrocchi, M. Tonani, M. Drudi, P. Nassisi, L. Conte, L. Panzera, A. Navarra, G. Negro
Publikováno v:
Natural Hazards and Earth System Sciences, Vol 17, Iss 4, Pp 533-547 (2017)
Reliable and timely information on the environmental conditions at sea is key to the safety of professional and recreational users as well as to the optimal execution of their activities. The possibility of users obtaining environmental information i
Externí odkaz:
https://doaj.org/article/c82391d3352a41f5afe299a6cfb8b361
Autor:
Jessica Fernandes Lopes, Victor G. Turrisi da Costa, Douglas F. Barbin, Luis Jam Pier Cruz-Tirado, Vincent Baeten, Sylvio Barbon Junior
Publikováno v:
Multimedia Tools and Applications. 81:41059-41077
Cocoa hybridisation generates new varieties which are resistant to several plant diseases, but has individual chemical characteristics that affect chocolate production. Image analysis is a useful method for visual discrimination of cocoa beans, while
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e74515673e65106685d68843b332ac88
https://doi.org/10.1007/s11042-022-13097-3
https://doi.org/10.1007/s11042-022-13097-3
Autor:
G. Coppini, E. Jansen, G. Turrisi, S. Creti, E. Y. Shchekinova, N. Pinardi, R. Lecci, I. Carluccio, Y. V. Kumkar, A. D'Anca, G. Mannarini, S. Martinelli, P. Marra, T. Capodiferro, T. Gismondi
Publikováno v:
Natural Hazards and Earth System Sciences, Vol 16, Iss 12, Pp 2713-2727 (2016)
A new web-based and mobile decision support system (DSS) for search-and-rescue (SAR) at sea is presented, and its performance is evaluated using real case scenarios. The system, named OCEAN-SAR, is accessible via the website http://www.ocean-sar.com.
Externí odkaz:
https://doaj.org/article/6acf3e36401f4efeb5e8e9dfcf5799c9
Autor:
G. Mannarini, G. Turrisi, A. D'Anca, M. Scalas, N. Pinardi, G. Coppini, F. Palermo, I. Carluccio, M. Scuro, S. Cretì, R. Lecci, P. Nassisi, L. Tedesco
Publikováno v:
Natural Hazards and Earth System Sciences, Vol 16, Iss 8, Pp 1791-1806 (2016)
VISIR (discoVerIng Safe and effIcient Routes) is an operational decision support system (DSS) for optimal ship routing designed and implemented in the frame of the TESSA (TEchnology for Situational Sea Awareness) project. The system is aimed to incre
Externí odkaz:
https://doaj.org/article/a3de8304506d4566a3bbdb9ecfe6b52f