no code implementations • 16 Apr 2024 • Mattia Litrico, Davide Talon, Sebastiano Battiato, Alessio Del Bue, Mario Valerio Giuffrida, Pietro Morerio
We propose a novel approach for SF-OSDA that exploits the granularity of target-private categories by segregating their samples into multiple unknown classes.
1 code implementation • 5 Dec 2023 • Camillo Quattrocchi, Antonino Furnari, Daniele Di Mauro, Mario Valerio Giuffrida, Giovanni Maria Farinella
Instead, we propose a novel methodology which performs the adaptation leveraging existing labeled exocentric videos and a new set of unlabeled, synchronized exocentric-egocentric video pairs, for which temporal action segmentation annotations do not need to be collected.
no code implementations • ICCV 2023 • Feng Chen, Mario Valerio Giuffrida, Sotirios A. Tsaftaris
The experimental results show that a foundation model can be efficiently adapted to multiple plant phenotyping tasks, yielding similar performance as the state-of-the-art (SoTA) models specifically designed or trained for each task.
no code implementations • 13 Jan 2023 • Peter Aaby, Mario Valerio Giuffrida, William J Buchanan, Zhiyuan Tan
This paper focuses on how touch interactions on smartphones can provide a continuous user authentication service through behaviour captured by a touchscreen.
no code implementations • 27 Jun 2022 • Bruno Casella, Alessio Barbaro Chisari, Sebastiano Battiato, Mario Valerio Giuffrida
The proposed aggregation loss allows our model to learn how trained deep network parameters can be aggregated with an aggregation operator.
1 code implementation • 5 Dec 2019 • Hao Chen, Mario Valerio Giuffrida, Peter Doerner, Sotirios A. Tsaftaris
We evaluate our method in several datasets in medical imaging, plant science, and remote sensing.
no code implementations • 5 Sep 2017 • Andrei Dobrescu, Mario Valerio Giuffrida, Sotirios A. Tsaftaris
While state-of-the-art results on leaf counting with deep learning methods have recently been reported, they obtain the count as a result of leaf segmentation and thus require per-leaf (instance) segmentation to train the models (a rather strong annotation).
no code implementations • 4 Sep 2017 • Mario Valerio Giuffrida, Hanno Scharr, Sotirios A. Tsaftaris
We show that our model is able to generate realistic 128x128 colour images of plants.
no code implementations • 28 Jun 2016 • Mario Valerio Giuffrida, Sotirios A. Tsaftaris
In this paper, we propose the Theta-Restricted Boltzmann Machine ({\theta}-RBM in short), which builds upon the original RBM formulation and injects the notion of rotation-invariance during the learning procedure.
no code implementations • 24 Apr 2016 • Mario Valerio Giuffrida, Sotirios A. Tsaftaris
Finding suitable features has been an essential problem in computer vision.