Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Cristiano Saltori"'
Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations. However, registering point cloud pairs in the case of partial overlap is still a challenge. This paper propose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8cf75b2d143e3c1e9b65c7fcc34b9137
http://arxiv.org/abs/2210.09836
http://arxiv.org/abs/2210.09836
Autor:
Cristiano Saltori, Evgeny Krivosheev, Stéphane Lathuiliére, Nicu Sebe, Fabio Galasso, Giuseppe Fiameni, Elisa Ricci, Fabio Poiesi
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198267
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5385ebd5a18eeab9294d43ee6e1fffce
https://hdl.handle.net/11573/1657985
https://hdl.handle.net/11573/1657985
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031198267
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9dfdda6ecd68ec532d34c82a629e2cee
https://doi.org/10.1007/978-3-031-19827-4_34
https://doi.org/10.1007/978-3-031-19827-4_34
Publikováno v:
Computer Vision and Image Understanding. 222:103485
Deep learning revolution happened thanks to the availability of a massive amount of labeled data which contributed to the development of models with extraordinary inference capabilities. Despite the public availability of large-scale datasets, to add
Publikováno v:
International Conference on 3D Vision
International Conference on 3D Vision, Nov 2020, Fukuoka, Japan
3DV
International Conference on 3D Vision, Nov 2020, Fukuoka, Japan
3DV
3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due to domain shift. In the case of LiDAR, in fact, domain shift is not o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d5409d4304ae860959dfa10c4bb04585
https://hal.telecom-paris.fr/hal-03108401
https://hal.telecom-paris.fr/hal-03108401
Autor:
Elisa Ricci, Federico Mento, Ruud J. G. van Sloun, Sebastiaan P. Oei, Iris A.M. Huijben, Giovanni Maschietto, Libertario Demi, Nishith Chennakeshava, Riccardo Inchingolo, Andrea Smargiassi, Andrea Passerini, Gino Soldati, Alessandro Sentelli, Enrico Fini, Ben Luijten, Willi Menapace, Subhankar Roy, Paolo Rota, Elena Torri, Cristiano Saltori, Riccardo Trevisan, Emanuele Peschiera
Publikováno v:
IEEE Transactions on Medical Imaging
IEEE Transactions on Medical Imaging, 39(8):9093068, 2676-2687. Institute of Electrical and Electronics Engineers
IEEE Transactions on Medical Imaging, 39(8):9093068, 2676-2687. Institute of Electrical and Electronics Engineers
Deep learning (DL) has proved successful in medical imaging and, in the wake of the recent COVID-19 pandemic, some works have started to investigate DL-based solutions for the assisted diagnosis of lung diseases. While existing works focus on CT scan
Publikováno v:
WIFS
Current developments in computer vision and deep learning allow to automatically generate hyper-realistic images, hardly distinguishable from real ones. In particular, human face generation achieved a stunning level of realism, opening new opportunit
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030306410
ICIAP (1)
ICIAP (1)
Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary algorithms
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::161f07019355cda5bf7d072b69e60759
https://doi.org/10.1007/978-3-030-30642-7_20
https://doi.org/10.1007/978-3-030-30642-7_20
Publikováno v:
Computer Vision and Image Understanding. 203:103126
Recurrent neural networks have shown good abilities in learning the spatio-temporal dependencies of moving agents in crowded scenes. Recently, they have been adopted to predict the motion of pedestrians by learning the relative motion of each individ