1 code implementation • IEEE Transactions on Artificial Intelligence 2024 • Federico Fontana, Romeo Lanzino, Marco Raoul Marini, Danilo Avola, Luigi Cinque, Francesco Scarcello, Gian Luca Foresti
Neural Networks (NNs) have been driving machine learning progress in recent years, but their larger models present challenges in resource-limited environments.
Ranked #25 on Image Classification on CIFAR-10 (Top-1 Accuracy metric)
no code implementations • 16 Jan 2024 • Silvia Zottin, Axel De Nardin, Emanuela Colombi, Claudio Piciarelli, Filippo Pavan, Gian Luca Foresti
Document Layout Analysis, which is the task of identifying different semantic regions inside of a document page, is a subject of great interest for both computer scientists and humanities scholars as it represents a fundamental step towards further analysis tasks for the former and a powerful tool to improve and facilitate the study of the documents for the latter.
no code implementations • 31 Jul 2023 • Hussain Ahmad Madni, Rao Muhammad Umer, Gian Luca Foresti
In this paper, we exploit the data and model heterogeneity simultaneously, and propose a method, MDH-FL (Exploiting Model and Data Heterogeneity in FL) to solve such problems to enhance the efficiency of the global model in FL.
no code implementations • 27 Oct 2022 • Axel De Nardin, Pankaj Mishra, Gian Luca Foresti, Claudio Piciarelli
Image anomaly detection consists in detecting images or image portions that are visually different from the majority of the samples in a dataset.
no code implementations • 27 Oct 2022 • Axel De Nardin, Silvia Zottin, Matteo Paier, Gian Luca Foresti, Emanuela Colombi, Claudio Piciarelli
Layout analysis is a task of uttermost importance in ancient handwritten document analysis and represents a fundamental step toward the simplification of subsequent tasks such as optical character recognition and automatic transcription.
no code implementations • 26 Mar 2022 • Danilo Avola, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti, Marco Raoul Marini, Alessio Mecca, Daniele Pannone
Taking medicines is a fundamental aspect to cure illnesses.
no code implementations • 18 Mar 2022 • Danilo Avola, Marco Cascio, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti, Marco Raoul Marini, Daniele Pannone
Nowadays, machine and deep learning techniques are widely used in different areas, ranging from economics to biology.
no code implementations • 11 Mar 2022 • Danilo Avola, Marco Cascio, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti
The latter conditions signal-based features in the visual domain to completely replace visual data.
no code implementations • 6 Oct 2021 • Danilo Avola, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti
Improving existing neural network architectures can involve several design choices such as manipulating the loss functions, employing a diverse learning strategy, exploiting gradient evolution at training time, optimizing the network hyper-parameters, or increasing the architecture depth.
no code implementations • 28 Sep 2021 • Danilo Avola, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti, Adriano Fragomeni, Daniele Pannone
Estimating the 3D pose of a hand from a 2D image is a well-studied problem and a requirement for several real-life applications such as virtual reality, augmented reality, and hand gesture recognition.
no code implementations • 1 Jul 2021 • Claudio Piciarelli, Gian Luca Foresti
The paper first defines a proper learning model for a single drone, and then extends it to the case of multiple drones both with greedy and cooperative strategies.
1 code implementation • 20 Apr 2021 • Pankaj Mishra, Riccardo Verk, Daniele Fornasier, Claudio Piciarelli, Gian Luca Foresti
We present a transformer-based image anomaly detection and localization network.
Ranked #9 on Anomaly Detection on BTAD (using extra training data)
1 code implementation • 4 Dec 2020 • Rita Pucci, Christian Micheloni, Gian Luca Foresti, Niki Martinel
Different from existing works relying on convolutional neural network models pre-trained with supervision, we cast such colourisation problem as a self-supervised learning task.
no code implementations • 12 Nov 2020 • Pankaj Mishra, Claudio Piciarelli, Gian Luca Foresti
Anomaly detection consists in identifying, within a dataset, those samples that significantly differ from the majority of the data, representing the normal class.
1 code implementation • 7 Sep 2020 • Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni
Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities.
1 code implementation • 3 May 2020 • Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni
Most current deep learning based single image super-resolution (SISR) methods focus on designing deeper / wider models to learn the non-linear mapping between low-resolution (LR) inputs and the high-resolution (HR) outputs from a large number of paired (LR/HR) training data.
no code implementations • 13 Apr 2020 • Enkhtogtokh Togootogtokh, Christian Micheloni, Gian Luca Foresti, Niki Martinel
In this paper we focus on this challenge and introduce a multi-layer AI (MLAI) framework to allow easy integration of ad-hoc visual-based AI applications.
no code implementations • 26 Sep 2019 • Marco Zamprogno, Marco Passon, Niki Martinel, Giuseppe Serra, Giuseppe Lancioni, Christian Micheloni, Carlo Tasso, Gian Luca Foresti
In this paper we consider the problem of video-based person re-identification, which is the task of associating videos of the same person captured by different and non-overlapping cameras.
no code implementations • 18 Sep 2019 • Matteo Dunnhofer, Niki Martinel, Gian Luca Foresti, Christian Micheloni
In the last decade many different algorithms have been proposed to track a generic object in videos.
no code implementations • 9 Sep 2019 • Rao Muhammad Umer, Gian Luca Foresti, Christian Micheloni
Single Image Super-Resolution (SISR) aims to generate a high-resolution (HR) image of a given low-resolution (LR) image.
1 code implementation • 6 Sep 2019 • Claudio Piciarelli, Pankaj Mishra, Gian Luca Foresti
Image anomaly detection consists in finding images with anomalous, unusual patterns with respect to a set of normal data.
no code implementations • 23 Jul 2019 • Danilo Avola, Luigi Cinque, Alessio Fagioli, Gian Luca Foresti, Cristiano Massaroni
In this paper, a solution for basic non-acted emotion recognition based on 3D skeleton and Deep Neural Networks (DNNs) is provided.
1 code implementation • International Conference on Computer Vision and Pattern Recognition Workshops (CVPR) 2019 • Niki Martinel, Gian Luca Foresti, Christian Micheloni
A surge of effort has been spent by the community to learn deep Re-ID models capturing a holistic single semantic level feature representation.
Ranked #18 on Person Re-Identification on Market-1501
no code implementations • 28 Mar 2018 • Danilo Avola, Marco Bernardi, Luigi Cinque, Gian Luca Foresti, Cristiano Massaroni
In human interactions, hands are a powerful way of expressing information that, in some cases, can be used as a valid substitute for voice, as it happens in Sign Language.
no code implementations • ICCV 2017 • Giuseppe Lisanti, Niki Martinel, Alberto del Bimbo, Gian Luca Foresti
First, a dictionary of sparse atoms is learned using patches extracted from single person images.
no code implementations • 5 Apr 2017 • Danilo Avola, Gian Luca Foresti, Niki Martinel, Daniele Pannone, Claudio Piciarelli
In recent years, the technological improvements of low-cost small-scale Unmanned Aerial Vehicles (UAVs) are promoting an ever-increasing use of them in different tasks.
4 code implementations • 20 Dec 2016 • Niki Martinel, Gian Luca Foresti, Christian Micheloni
We believe that better results can be obtained if the deep architecture is defined with respect to an analysis of the food composition.