Zobrazeno 1 - 10
of 2 051
pro vyhledávání: '"Panariello, 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
We introduce 2D-Malafide, a novel and lightweight adversarial attack designed to deceive face deepfake detection systems. Building upon the concept of 1D convolutional perturbations explored in the speech domain, our method leverages 2D convolutional
Externí odkaz:
http://arxiv.org/abs/2408.14143
Autor:
Todisco, Massimiliano, Panariello, Michele, Wang, Xin, Delgado, Héctor, Lee, Kong Aik, Evans, Nicholas
We present Malacopula, a neural-based generalised Hammerstein model designed to introduce adversarial perturbations to spoofed speech utterances so that they better deceive automatic speaker verification (ASV) systems. Using non-linear processes to m
Externí odkaz:
http://arxiv.org/abs/2408.09300
Voice anonymisation can be used to help protect speaker privacy when speech data is shared with untrusted others. In most practical applications, while the voice identity should be sanitised, other attributes such as the spoken content should be pres
Externí odkaz:
http://arxiv.org/abs/2408.04306
Autor:
Frascaroli, Emanuele, Panariello, Aniello, Buzzega, Pietro, Bonicelli, Lorenzo, Porrello, Angelo, Calderara, Simone
With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting strategies t
Externí odkaz:
http://arxiv.org/abs/2407.15793
Autor:
Panariello, Michele, Tomashenko, Natalia, Wang, Xin, Miao, Xiaoxiao, Champion, Pierre, Nourtel, Hubert, Todisco, Massimiliano, Evans, Nicholas, Vincent, Emmanuel, Yamagishi, Junichi
The VoicePrivacy Challenge promotes the development of voice anonymisation solutions for speech technology. In this paper we present a systematic overview and analysis of the second edition held in 2022. We describe the voice anonymisation task and d
Externí odkaz:
http://arxiv.org/abs/2407.11516
Autor:
Mosconi, Matteo, Sorokin, Andriy, Panariello, Aniello, Porrello, Angelo, Bonato, Jacopo, Cotogni, Marco, Sabetta, Luigi, Calderara, Simone, Cucchiara, Rita
The use of skeletal data allows deep learning models to perform action recognition efficiently and effectively. Herein, we believe that exploring this problem within the context of Continual Learning is crucial. While numerous studies focus on skelet
Externí odkaz:
http://arxiv.org/abs/2407.01397
Autor:
Tomashenko, Natalia, Miao, Xiaoxiao, Champion, Pierre, Meyer, Sarina, Wang, Xin, Vincent, Emmanuel, Panariello, Michele, Evans, Nicholas, Yamagishi, Junichi, Todisco, Massimiliano
The task of the challenge is to develop a voice anonymization system for speech data which conceals the speaker's voice identity while protecting linguistic content and emotional states. The organizers provide development and evaluation datasets and
Externí odkaz:
http://arxiv.org/abs/2404.02677
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
Autor:
Kaili Chen, Adrian Najer, Patrick Charchar, Catherine Saunders, Chalaisorn Thanapongpibul, Anna Klöckner, Mohamed Chami, David J. Peeler, Inês Silva, Luca Panariello, Kersti Karu, Colleen N. Loynachan, Leah C. Frenette, Michael Potter, John S. Tregoning, Ivan P. Parkin, Andrew M. Edwards, Thomas B. Clarke, Irene Yarovsky, Molly M. Stevens
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-18 (2024)
Abstract Staphylococcus aureus is a leading cause of nosocomial implant-associated infections, causing significant morbidity and mortality, underscoring the need for rapid, non-invasive, and cost-effective diagnostics. Here, we optimise the synthesis
Externí odkaz:
https://doaj.org/article/cce09cda3cc44bc1a4d83bbce5d35001
