Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Luca Cosmo"'
Autor:
Tomer Weiss, Luca Cosmo, Eduardo Mayo Yanes, Sabyasachi Chakraborty, Alex M. Bronstein, Renana Gershoni-Poranne
The holy grail of materials science is de novo molecular design -- i.e., the ability to engineer molecules with desired characteristics. Recently, this goal has become increasingly achievable thanks to developments such as equivariant graph neural ne
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::db68a5d04900c037d6b8dfa9aa112090
https://doi.org/10.26434/chemrxiv-2023-z8ltp
https://doi.org/10.26434/chemrxiv-2023-z8ltp
Publikováno v:
International Journal of Computer Vision. 130:1474-1493
The Average Mixing Kernel Signature is a novel spectral signature for points on non-rigid three-dimensional shapes. It is based on a quantum exploration process of the shape surface, where the average transition probabilities between the points of th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e8962a687549ac7ef72d10fe8437b12
https://doi.org/10.1007/s11263-022-01610-y
https://doi.org/10.1007/s11263-022-01610-y
Autor:
Kamilia Zaripova, Luca Cosmo, Anees Kazi, Seyed-Ahmad Ahmadi, Michael M. Bronstein, Nassir Navab
Graphs are a powerful tool for representing and analyzing unstructured, non-Euclidean data ubiquitous in the healthcare domain. Two prominent examples are molecule property prediction and brain connectome analysis. Importantly, recent works have show
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::266613b623dcc627b0fbfdabe506b782
http://arxiv.org/abs/2204.00323
http://arxiv.org/abs/2204.00323
Publikováno v:
Computer Graphics Forum
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d67215b14c16827faef05ef26bf1e8d9
https://doi.org/10.1111/cgf.14083
https://doi.org/10.1111/cgf.14083
Graph deep learning has recently emerged as a powerful ML concept allowing to generalize successful deep neural architectures to non-Euclidean structured data. Such methods have shown promising results on a broad spectrum of applications ranging from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::24b25ee52f2898786ec3570fbc5fc12f
http://hdl.handle.net/10278/3759611
http://hdl.handle.net/10278/3759611
Autor:
Luca Moschella, Simone Melzi, Luca Cosmo, Filippo Maggioli, Or Litany, Maks Ovsjanikov, Leonidas Guibas, Emanuele Rodolà
Spectral geometric methods have brought revolutionary changes to the field of geometry processing. Of particular interest is the study of the Laplacian spectrum as a compact, isometry and permutation-invariant representation of a shape. Some recent w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::47d9e7b6189b6331944ae75c2f1fc57b
https://hdl.handle.net/10278/5002939
https://hdl.handle.net/10278/5002939
Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between meshes that have a certain degree of deformation. Existing methods either consider the local des
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::89eb2380295e97d2a264f875a8511ef7
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031230271
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b50f03562d77cf18aafb83cfe3ca08b
https://doi.org/10.1007/978-3-031-23028-8_5
https://doi.org/10.1007/978-3-031-23028-8_5
Autor:
Giovanni Trappolini, Luca Cosmo, Luca Moschella, Riccardo Marin, Simone Melzi, Emanuele Rodolà
Publikováno v:
Scopus-Elsevier
Sapienza Università di Roma-IRIS
Sapienza Università di Roma-IRIS
In this paper, we propose a transformer-based procedure for the efficient registration of non-rigid 3D point clouds. The proposed approach is data-driven and adopts for the first time the transformer architecture in the registration task. Our method
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::58c9723a839afbc564378a6dcc11412d
http://arxiv.org/abs/2106.13679
http://arxiv.org/abs/2106.13679
Publikováno v:
CVPR
Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong predictions despite being imperceptible. However, the existence of "universal" attacks (i.e., unique perturbations that tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64def982089c11087f25a7b4234ccfa1
http://arxiv.org/abs/2104.03356
http://arxiv.org/abs/2104.03356