Zobrazeno 1 - 10
of 191
pro vyhledávání: '"Farella, Elisabetta"'
Autor:
Barusco, Manuel, Borsatti, Francesco, Pezze, Davide Dalle, Paissan, Francesco, Farella, Elisabetta, Susto, Gian Antonio
Visual Anomaly Detection (VAD) has gained significant research attention for its ability to identify anomalous images and pinpoint the specific areas responsible for the anomaly. A key advantage of VAD is its unsupervised nature, which eliminates the
Externí odkaz:
http://arxiv.org/abs/2410.11591
Autor:
De Monte, Riccardo, Pezze, Davide Dalle, Ceccon, Marina, Pasti, Francesco, Paissan, Francesco, Farella, Elisabetta, Susto, Gian Antonio, Bellotto, Nicola
Object Detection is a highly relevant computer vision problem with many applications such as robotics and autonomous driving. Continual Learning~(CL) considers a setting where a model incrementally learns new information while retaining previously ac
Externí odkaz:
http://arxiv.org/abs/2409.05650
Autor:
Pasti, Francesco, Ceccon, Marina, Pezze, Davide Dalle, Paissan, Francesco, Farella, Elisabetta, Susto, Gian Antonio, Bellotto, Nicola
While numerous methods achieving remarkable performance exist in the Object Detection literature, addressing data distribution shifts remains challenging. Continual Learning (CL) offers solutions to this issue, enabling models to adapt to new data wh
Externí odkaz:
http://arxiv.org/abs/2409.01872
Contrastive Language-Audio Pretraining (CLAP) became of crucial importance in the field of audio and speech processing. Its employment ranges from sound event detection to text-to-audio generation. However, one of the main limitations is the consider
Externí odkaz:
http://arxiv.org/abs/2311.14517
Autor:
Martín-Morató, Irene, Paissan, Francesco, Ancilotto, Alberto, Heittola, Toni, Mesaros, Annamaria, Farella, Elisabetta, Brutti, Alessio, Virtanen, Tuomas
This paper presents an analysis of the Low-Complexity Acoustic Scene Classification task in DCASE 2022 Challenge. The task was a continuation from the previous years, but the low-complexity requirements were changed to the following: the maximum numb
Externí odkaz:
http://arxiv.org/abs/2206.03835
Autor:
Cerutti, Gianmarco, Cavigelli, Lukas, Andri, Renzo, Magno, Michele, Farella, Elisabetta, Benini, Luca
Keyword spotting (KWS) is a crucial function enabling the interaction with the many ubiquitous smart devices in our surroundings, either activating them through wake-word or directly as a human-computer interface. For many applications, KWS is the en
Externí odkaz:
http://arxiv.org/abs/2201.03386
In the Internet of Things era, where we see many interconnected and heterogeneous mobile and fixed smart devices, distributing the intelligence from the cloud to the edge has become a necessity. Due to limited computational and communication capabili
Externí odkaz:
http://arxiv.org/abs/2110.00337
The Internet of Things (IoT) and smart city paradigm includes ubiquitous technology to extract context information in order to return useful services to users and citizens. An essential role in this scenario is often played by computer vision applica
Externí odkaz:
http://arxiv.org/abs/2102.01340
Autor:
Cerutti, Gianmarco, Andri, Renzo, Cavigelli, Lukas, Magno, Michele, Farella, Elisabetta, Benini, Luca
Sound event detection (SED) is a hot topic in consumer and smart city applications. Existing approaches based on Deep Neural Networks are very effective, but highly demanding in terms of memory, power, and throughput when targeting ultra-low power al
Externí odkaz:
http://arxiv.org/abs/2101.04446
Outdoor acoustic events detection is an exciting research field but challenged by the need for complex algorithms and deep learning techniques, typically requiring many computational, memory, and energy resources. This challenge discourages IoT imple
Externí odkaz:
http://arxiv.org/abs/2001.10876