Luca Cosmo | DeepAI

DeepAI AI Chat

Featured Co-authors

Nassir Navab
318 publications
Daniel Cremers
177 publications
Federico Tombari
130 publications
Leonidas Guibas
102 publications
Michael M. Bronstein
60 publications
Benjamin Busam
59 publications
Maks Ovsjanikov
53 publications
Ron Kimmel
52 publications
Emanuele Rodolà
52 publications
Or Litany
50 publications
Michael Bronstein
38 publications

∙ 02/04/2023

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

In this work, we define a diffusion-based generative model capable of bo...

0 Giorgio Mariani, et al. ∙

∙ 01/09/2023

Latent Autoregressive Source Separation

Autoregressive models have achieved impressive results over a wide range...

0 Emilian Postolache, et al. ∙

∙ 05/30/2022

Harnessing spectral representations for subgraph alignment

With the rise and advent of graph learning techniques, graph data has be...

0 Marco Pegoraro, et al. ∙

∙ 04/01/2022

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Graphs are a powerful tool for representing and analyzing unstructured, ...

13 Kamilia Mullakaeva, et al. ∙

∙ 02/03/2022

Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport

Shape matching has been a long-studied problem for the computer graphics...

0 Mahdi Saleh, et al. ∙

∙ 12/14/2021

Graph Kernel Neural Networks

The convolution operator at the core of many modern neural architectures...

194 Luca Cosmo, et al. ∙

∙ 10/11/2021

Unsupervised Source Separation via Bayesian Inference in the Latent Domain

State of the art audio source separation models rely on supervised data-...

0 Michele Mancusi, et al. ∙

∙ 06/25/2021

Shape registration in the time of transformers

In this paper, we propose a transformer-based procedure for the efficien...

6 Giovanni Trappolini, et al. ∙

∙ 04/07/2021

Universal Spectral Adversarial Attacks for Deformable Shapes

Machine learning models are known to be vulnerable to adversarial attack...

0 Arianna Rampini, et al. ∙

∙ 03/31/2021

Spectral Unions of Partial Deformable 3D Shapes

Spectral geometric methods have brought revolutionary changes to the fie...

9 Luca Moschella, et al. ∙

∙ 03/02/2021

Learning disentangled representations via product manifold projection

We propose a novel approach to disentangle the generative factors of var...

0 Marco Fumero, et al. ∙

∙ 03/27/2020

LIMP: Learning Latent Shape Representations with Metric Preservation Priors

In this paper, we advocate the adoption of metric preservation as a powe...

0 Luca Cosmo, et al. ∙

∙ 03/27/2020

Latent Patient Network Learning for Automatic Diagnosis

Recently, Graph Convolutional Networks (GCNs) has proven to be a powerfu...

0 Luca Cosmo, et al. ∙

∙ 02/11/2020

Differentiable Graph Module (DGM) Graph Convolutional Networks

Graph deep learning has recently emerged as a powerful ML concept allowi...

36 Anees Kazi, et al. ∙

∙ 11/28/2018

Isospectralization, or how to hear shape, style, and correspondence

The question whether one can recover the shape of a geometric object fro...

4 Luca Cosmo, et al. ∙

∙ 06/17/2015

Partial Functional Correspondence

In this paper, we propose a method for computing partial functional corr...

0 Emanuele Rodolà, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world