Zobrazeno 1 - 10
of 3 890
pro vyhledávání: '"Mancusi A"'
Autor:
Mancusi, Gianluca, Bernardi, Mattia, Panariello, Aniello, Porrello, Angelo, Cucchiara, Rita, Calderara, Simone
End-to-end transformer-based trackers have achieved remarkable performance on most human-related datasets. However, training these trackers in heterogeneous scenarios poses significant challenges, including negative interference - where the model lea
Externí odkaz:
http://arxiv.org/abs/2411.00553
Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and high-frequency harmonic
Externí odkaz:
http://arxiv.org/abs/2409.11145
Autor:
Mancusi, Michele, Halychanskyi, Yurii, Cheuk, Kin Wai, Lai, Chieh-Hsin, Uhlich, Stefan, Koo, Junghyun, Martínez-Ramírez, Marco A., Liao, Wei-Hsiang, Fabbro, Giorgio, Mitsufuji, Yuki
Music timbre transfer is a challenging task that involves modifying the timbral characteristics of an audio signal while preserving its melodic structure. In this paper, we propose a novel method based on dual diffusion bridges, trained using the Coc
Externí odkaz:
http://arxiv.org/abs/2409.06096
Autor:
Ciranni, Ruben, Mariani, Giorgio, Mancusi, Michele, Postolache, Emilian, Fabbro, Giorgio, Rodolà, Emanuele, Cosmo, Luca
We present COCOLA (Coherence-Oriented Contrastive Learning for Audio), a contrastive learning method for musical audio representations that captures the harmonic and rhythmic coherence between samples. Our method operates at the level of the stems co
Externí odkaz:
http://arxiv.org/abs/2404.16969
Autor:
Panariello, Aniello, Mancusi, Gianluca, Ali, Fedy Haj, Porrello, Angelo, Calderara, Simone, Cucchiara, Rita
Accurate per-object distance estimation is crucial in safety-critical applications such as autonomous driving, surveillance, and robotics. Existing approaches rely on two scales: local information (i.e., the bounding box proportions) or global inform
Externí odkaz:
http://arxiv.org/abs/2401.03191
The investigation of correlations in Monte Carlo power iteration has been long dominated by the question of generational correlations and their effects on the estimation of statistical uncertainties. More recently, there has been a growing interest i
Externí odkaz:
http://arxiv.org/abs/2309.03767
Autor:
Serena Renzi, Luca Digiacomo, Daniela Pozzi, Erica Quagliarini, Elisabetta Vulpis, Maria Valeria Giuli, Angelica Mancusi, Bianca Natiello, Maria Gemma Pignataro, Gianluca Canettieri, Laura Di Magno, Luca Pesce, Valentina De Lorenzi, Samuele Ghignoli, Luisa Loconte, Carmela Maria Montone, Anna Laura Capriotti, Aldo Laganà, Carmine Nicoletti, Heinz Amenitsch, Marco Rossi, Francesco Mura, Giacomo Parisi, Francesco Cardarelli, Alessandra Zingoni, Saula Checquolo, Giulio Caracciolo
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-20 (2024)
Abstract Lipid nanoparticles (LNPs) play a crucial role in addressing genetic disorders, and cancer, and combating pandemics such as COVID-19 and its variants. Yet, the ability of LNPs to effectively encapsulate large-size DNA molecules remains elusi
Externí odkaz:
https://doaj.org/article/0ac4519bb8ec417189f0144fcc73185a
Autor:
Alessio Mosca, Stefania Chiappini, Andrea Miuli, Gianluca Mancusi, Clara Cavallotto, John M. Corkery, Livia Miotti, Mauro Pettorruso, Giovanni Martinotti, Fabrizio Schifano
Publikováno v:
Psychiatry International, Vol 5, Iss 3, Pp 552-563 (2024)
Background: Piperazines, synthetic compounds known for their stimulant and hallucinogenic effects, have gained prominence among novel psychoactive substances (NPS) and are frequently associated with adverse psychiatric outcomes, including psychosis.
Externí odkaz:
https://doaj.org/article/39388fd0802640c5874764307eec6c5f
Autor:
Mancusi, Gianluca, Panariello, Aniello, Porrello, Angelo, Fabbri, Matteo, Calderara, Simone, Cucchiara, Rita
The field of multi-object tracking has recently seen a renewed interest in the good old schema of tracking-by-detection, as its simplicity and strong priors spare it from the complex design and painful babysitting of tracking-by-attention approaches.
Externí odkaz:
http://arxiv.org/abs/2308.11513
Autor:
Santilli, Andrea, Severino, Silvio, Postolache, Emilian, Maiorca, Valentino, Mancusi, Michele, Marin, Riccardo, Rodolà, Emanuele
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and require changes to the MT model,
Externí odkaz:
http://arxiv.org/abs/2305.10427