Zobrazeno 1 - 10
of 1 703
pro vyhledávání: '"Falchi, P. P."'
Autor:
Pacini, Giacomo, Carrara, Fabio, Messina, Nicola, Tonellotto, Nicola, Amato, Giuseppe, Falchi, Fabrizio
Query suggestion, a technique widely adopted in information retrieval, enhances system interactivity and the browsing experience of document collections. In cross-modal retrieval, many works have focused on retrieving relevant items from natural lang
Externí odkaz:
http://arxiv.org/abs/2412.13834
We propose a novel two-stage semi-supervised learning approach for training downsampling-upsampling semantic segmentation architectures. The first stage does not use backpropagation. Rather, it exploits the bio-inspired Hebbian principle "fire togeth
Externí odkaz:
http://arxiv.org/abs/2412.03192
Autor:
Barsellotti, Luca, Bianchi, Lorenzo, Messina, Nicola, Carrara, Fabio, Cornia, Marcella, Baraldi, Lorenzo, Falchi, Fabrizio, Cucchiara, Rita
Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse spatial informat
Externí odkaz:
http://arxiv.org/abs/2411.19331
Autor:
Coccomini, Davide Alessandro, Caldelli, Roberto, Falchi, Fabrizio, Gennaro, Claudio, Amato, Giuseppe
Image manipulation is rapidly evolving, allowing the creation of credible content that can be used to bend reality. Although the results of deepfake detectors are promising, deepfakes can be made even more complicated to detect through adversarial at
Externí odkaz:
http://arxiv.org/abs/2410.04205
Autor:
Ciampi, Luca, Messina, Nicola, Pierucci, Matteo, Amato, Giuseppe, Avvenuti, Marco, Falchi, Fabrizio
Recently, object counting has shifted towards class-agnostic counting (CAC), which counts instances of arbitrary object classes never seen during model training. With advancements in robust vision-and-language foundation models, there is a growing in
Externí odkaz:
http://arxiv.org/abs/2409.15953
Pose-estimation methods enable extracting human motion from common videos in the structured form of 3D skeleton sequences. Despite great application opportunities, effective content-based access to such spatio-temporal motion data is a challenging pr
Externí odkaz:
http://arxiv.org/abs/2407.02104
Autor:
Coccomini, Davide Alessandro, Caldelli, Roberto, Amato, Giuseppe, Falchi, Fabrizio, Gennaro, Claudio
Deepfake technology is rapidly advancing, posing significant challenges to the detection of manipulated media content. Parallel to that, some adversarial attack techniques have been developed to fool the deepfake detectors and make deepfakes even mor
Externí odkaz:
http://arxiv.org/abs/2407.02670
Animal behavior serves as a reliable indicator of the adaptation of organisms to their environment and their overall well-being. Through rigorous observation of animal actions and interactions, researchers and observers can glean valuable insights in
Externí odkaz:
http://arxiv.org/abs/2405.14002
Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains like extended reality, robotics, and autonomous driving, which require
Externí odkaz:
http://arxiv.org/abs/2404.03539
Autor:
Coccomini, Davide Alessandro, Caldelli, Roberto, Gennaro, Claudio, Fiameni, Giuseppe, Amato, Giuseppe, Falchi, Fabrizio
Deepfake detectors are typically trained on large sets of pristine and generated images, resulting in limited generalization capacity; they excel at identifying deepfakes created through methods encountered during training but struggle with those gen
Externí odkaz:
http://arxiv.org/abs/2403.13479