2 code implementations • 4 Apr 2024 • Lorenzo Bianchi, Fabio Carrara, Nicola Messina, Fabrizio Falchi
Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training.
no code implementations • 20 Mar 2024 • Davide Alessandro Coccomini, Roberto Caldelli, Claudio Gennaro, Giuseppe Fiameni, Giuseppe Amato, Fabrizio Falchi
We propose to train detectors using only pristine images injecting in part of them crafted frequency patterns, simulating the effects of various deepfake generation techniques without being specific to any.
1 code implementation • 29 Nov 2023 • Lorenzo Bianchi, Fabio Carrara, Nicola Messina, Claudio Gennaro, Fabrizio Falchi
Recent advancements in large vision-language models enabled visual object detection in open-vocabulary scenarios, where object classes are defined in free-text formats during inference.
no code implementations • 30 Jul 2023 • Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
For a long time, biology and neuroscience fields have been a great source of inspiration for computer scientists, towards the development of Artificial Intelligence (AI) technologies.
no code implementations • 30 Jul 2023 • Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Recently emerged technologies based on Deep Learning (DL) achieved outstanding results on a variety of tasks in the field of Artificial Intelligence (AI).
1 code implementation • 25 May 2023 • Nicola Messina, Jan Sedmidubsky, Fabrizio Falchi, Tomáš Rebok
Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences.
no code implementations • 28 Apr 2023 • Alessio Serra, Fabio Carrara, Maurizio Tesconi, Fabrizio Falchi
Trends and opinion mining in social media increasingly focus on novel interactions involving visual media, like images and short videos, in addition to text.
1 code implementation • 9 Mar 2023 • Davide Alessandro Coccomini, Andrea Esuli, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
This paper explores the task of detecting images generated by text-to-image diffusion models.
1 code implementation • 20 Nov 2022 • Davide Alessandro Coccomini, Giorgos Kordopatis Zilos, Giuseppe Amato, Roberto Caldelli, Fabrizio Falchi, Symeon Papadopoulos, Claudio Gennaro
In this paper, we introduce MINTIME, a video deepfake detection approach that captures spatial and temporal anomalies and handles instances of multiple people in the same video and variations in face sizes.
Ranked #1 on Classification on ForgeryNet
no code implementations • 4 Nov 2022 • Fabio Carrara, Fabrizio Falchi, Maria Girardi, Nicola Messina, Cristina Padovani, Daniele Pellegrini
Thanks to recent advancements in numerical methods, computer power, and monitoring technology, seismic ambient noise provides precious information about the structural behavior of old buildings.
no code implementations • 24 Aug 2022 • Marco Avvenuti, Marco Bongiovanni, Luca Ciampi, Fabrizio Falchi, Claudio Gennaro, Nicola Messina
Automatic people counting from images has recently drawn attention for urban monitoring in modern Smart Cities due to the ubiquity of surveillance camera networks.
1 code implementation • 29 Jul 2022 • Nicola Messina, Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Fabrizio Falchi, Giuseppe Amato, Rita Cucchiara
In literature, this task is often used as a pre-training objective to forge architectures able to jointly deal with images and texts.
Ranked #22 on Cross-Modal Retrieval on COCO 2014
2 code implementations • 28 Jun 2022 • Davide Alessandro Coccomini, Roberto Caldelli, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Deepfake Generation Techniques are evolving at a rapid pace, making it possible to create realistic manipulated images and videos and endangering the serenity of modern society.
2 code implementations • 21 Jun 2022 • Nicola Messina, Davide Alessandro Coccomini, Andrea Esuli, Fabrizio Falchi
With the increased accessibility of web and online encyclopedias, the amount of data to manage is constantly increasing.
no code implementations • 18 May 2022 • Gabriele Lagani, Davide Bacciu, Claudio Gallicchio, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR).
no code implementations • 15 Mar 2022 • Donato Cafarelli, Luca Ciampi, Lucia Vadicamo, Claudio Gennaro, Andrea Berton, Marco Paterni, Chiara Benvenuti, Mirko Passera, Fabrizio Falchi
Modern Unmanned Aerial Vehicles (UAV) equipped with cameras can play an essential role in speeding up the identification and rescue of people who have fallen overboard, i. e., man overboard (MOB).
no code implementations • 29 Nov 2021 • Nicola Messina, Giuseppe Amato, Fabio Carrara, Claudio Gennaro, Fabrizio Falchi
In the end, this study can lay the basis for a deeper understanding of the role of attention and recurrent connections for solving visual abstract reasoning tasks.
1 code implementation • 22 Nov 2021 • Davide Coccomini, Nicola Messina, Claudio Gennaro, Fabrizio Falchi
Space exploration has always been a source of inspiration for humankind, and thanks to modern telescopes, it is now possible to observe celestial bodies far away from us.
1 code implementation • SEMEVAL 2021 • Nicola Messina, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
This paper describes the system used by the AIMH Team to approach the SemEval Task 6.
3 code implementations • 6 Jul 2021 • Davide Coccomini, Nicola Messina, Claudio Gennaro, Fabrizio Falchi
Traditionally, Convolutional Neural Networks (CNNs) have been used to perform video deepfake detection, with the best results obtained using methods based on EfficientNet B7.
Ranked #1 on DeepFake Detection on DFDC (using extra training data)
1 code implementation • 6 Jul 2021 • Fabio Valerio Massoli, Lucia Vadicamo, Giuseppe Amato, Fabrizio Falchi
In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development.
no code implementations • 5 Jun 2021 • Luca Ciampi, Claudio Gennaro, Fabio Carrara, Fabrizio Falchi, Claudio Vairo, Giuseppe Amato
This paper presents a novel solution to automatically count vehicles in a parking lot using images captured by smart cameras.
no code implementations • 1 Jun 2021 • Nicola Messina, Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro, Stéphane Marchand-Maillet
It is designed for producing fixed-size 1024-d vectors describing whole images and sentences, as well as variable-length sets of 1024-d vectors describing the various building components of the two modalities (image regions and sentence words respectively).
1 code implementation • 6 May 2021 • Fabio Valerio Massoli, Donato Cafarelli, Claudio Gennaro, Giuseppe Amato, Fabrizio Falchi
Since the FER task involves analyzing face images that can be acquired with heterogeneous sources, thus involving images with different quality, it is plausible to expect that resolution plays an important role in such a case too.
no code implementations • 16 Mar 2021 • Gabriele Lagani, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
We propose to address the issue of sample efficiency, in Deep Convolutional Neural Networks (DCNN), with a semi-supervised training strategy that combines Hebbian learning with gradient descent: all internal layers (both convolutional and fully connected) are pre-trained using an unsupervised approach based on Hebbian learning, and the last fully connected layer (the classification layer) is trained using Stochastic Gradient Descent (SGD).
1 code implementation • 9 Mar 2021 • Fabio Valerio Massoli, Donato Cafarelli, Giuseppe Amato, Fabrizio Falchi
Facial expressions play a fundamental role in human communication.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 22 Jan 2021 • Nicola Messina, Giuseppe Amato, Fabio Carrara, Claudio Gennaro, Fabrizio Falchi
With the experiments carried out in this work, we demonstrate that residual connections, and more generally the skip connections, seem to have only a marginal impact on the learning of the proposed problems.
no code implementations • 22 Jan 2021 • Donato Cafarelli, Fabio Valerio Massoli, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
The main goal of this work is to define a baseline for a novel method we are going to propose in the near future.
1 code implementation • 22 Dec 2020 • Gabriele Lagani, Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro
In particular, it has been shown that Hebbian learning can be used for training the lower or the higher layers of a neural network.
1 code implementation • 18 Dec 2020 • Gabriele Lagani, Raffaele Mazziotti, Fabrizio Falchi, Claudio Gennaro, Guido Marco Cicchini, Tommaso Pizzorusso, Federico Cremisi, Giuseppe Amato
Previous work has shown that it is possible to train neuronal cultures on Multi-Electrode Arrays (MEAs), to recognize very simple patterns.
Cultural Vocal Bursts Intensity Prediction Handwritten Digit Recognition
1 code implementation • 9 Dec 2020 • Fabio Valerio Massoli, Fabrizio Falchi, Alperen Kantarcı, Şeymanur Aktı, Hazim Kemal Ekenel, Giuseppe Amato
Indeed, differently from commonly used approaches that consider a neural network as a single computational block, i. e., using the output of the last layer only, MOCCA explicitly leverages the multi-layer structure of deep architectures.
Ranked #80 on Anomaly Detection on MVTec AD
1 code implementation • 16 Nov 2020 • Fabio Carrara, Giuseppe Amato, Luca Brombin, Fabrizio Falchi, Claudio Gennaro
In this work, we propose CBiGAN -- a novel method for anomaly detection in images, where a consistency constraint is introduced as a regularization term in both the encoder and decoder of a BiGAN.
1 code implementation • 12 Aug 2020 • Nicola Messina, Giuseppe Amato, Andrea Esuli, Fabrizio Falchi, Claudio Gennaro, Stéphane Marchand-Maillet
In this work, we tackle the task of cross-modal retrieval through image-sentence matching based on word-region alignments, using supervision only at the global image-sentence level.
Ranked #6 on Image Retrieval on Flickr30K 1K test
no code implementations • 6 Aug 2020 • Giuseppe Amato, Paolo Bolettieri, Fabio Carrara, Franca Debole, Fabrizio Falchi, Claudio Gennaro, Lucia Vadicamo, Claudio Vairo
In this paper, we describe in details VISIONE, a video search system that allows users to search for videos using textual keywords, occurrence of objects and their spatial relationships, occurrence of colors and their spatial relationships, and image similarity.
1 code implementation • 31 Jul 2020 • Tiziano Fagni, Fabrizio Falchi, Margherita Gambini, Antonio Martella, Maurizio Tesconi
To prevent this, it is crucial to develop deepfake social media messages detection systems.
1 code implementation • 13 Jul 2020 • Danilo Sorano, Fabio Carrara, Paolo Cintia, Fabrizio Falchi, Luca Pappalardo
In this paper, we describe PassNet, a method to recognize the most frequent events in soccer, i. e., passes, from video streams.
1 code implementation • 20 Apr 2020 • Nicola Messina, Fabrizio Falchi, Andrea Esuli, Giuseppe Amato
State-of-the-art results in image-text matching are achieved by inter-playing image and text features from the two different processing pipelines, usually using mutual attention mechanisms.
no code implementations • 9 Jan 2020 • Luca Ciampi, Nicola Messina, Fabrizio Falchi, Claudio Gennaro, Giuseppe Amato
Furthermore, we demonstrate that with our Domain Adaptation techniques, we can reduce the Synthetic2Real Domain Shift, making closer the two domains and obtaining a performance improvement when testing the network over the real-world images.
1 code implementation • 5 Dec 2019 • Fabio Valerio Massoli, Fabio Carrara, Giuseppe Amato, Fabrizio Falchi
In this frame, the contribution of our work is four-fold: i) we tested our recently proposed adversarial detection approach against classifier attacks, i. e. adversarial samples crafted to fool a FR neural network acting as a classifier; ii) using a k-Nearest Neighbor (kNN) algorithm as a guidance, we generated deep features attacks against a FR system based on a DL model acting as features extractor, followed by a kNN which gives back the query identity based on features similarity; iii) we used the deep features attacks to fool a FR system on the 1:1 Face Verification task and we showed their superior effectiveness with respect to classifier attacks in fooling such type of system; iv) we used the detectors trained on classifier attacks to detect deep features attacks, thus showing that such approach is generalizable to different types of offensives.
1 code implementation • 5 Dec 2019 • Fabio Valerio Massoli, Giuseppe Amato, Fabrizio Falchi
To the best of our knowledge, this is the first work testing extensively the performance of a FR model in a cross-resolution scenario; iii) we tested our models on the low resolution and low quality datasets QMUL-SurvFace and TinyFace and showed their superior performances, even though we did not train our model on low-resolution faces only and our main focus was cross-resolution; iv) we showed that our approach can be more effective with respect to preprocessing faces with super resolution techniques.
no code implementations • 10 May 2019 • Giuseppe Amato, Malte Behrmann, Frédéric Bimbot, Baptiste Caramiaux, Fabrizio Falchi, Ander Garcia, Joost Geurts, Jaume Gibert, Guillaume Gravier, Hadmut Holken, Hartmut Koenitz, Sylvain Lefebvre, Antoine Liutkus, Fabien Lotte, Andrew Perkis, Rafael Redondo, Enrico Turrin, Thierry Vieville, Emmanuel Vincent
Thanks to the Big Data revolution and increasing computing capacities, Artificial Intelligence (AI) has made an impressive revival over the past few years and is now omnipresent in both research and industry.
no code implementations • 20 Apr 2017 • Fabio Carrara, Andrea Esuli, Fabrizio Falchi, Alejandro Moreo Fernández
The recently proposed stochastic residual networks selectively activate or bypass the layers during training, based on independent stochastic choices, each of which following a probability distribution that is fixed in advance.
no code implementations • 2 Aug 2016 • Giuseppe Amato, Fabrizio Falchi, Lucia Vadicamo
Content-Based Image Retrieval based on local features is computationally expensive because of the complexity of both extraction and matching of local feature.
2 code implementations • 23 Jun 2016 • Fabio Carrara, Andrea Esuli, Tiziano Fagni, Fabrizio Falchi, Alejandro Moreo Fernández
We choose to implement the actual search process as a similarity search in a visual feature space, by learning to translate a textual query into a visual representation.
no code implementations • 19 Apr 2016 • Giuseppe Amato, Paolo Bolettieri, Fabrizio Falchi, Claudio Gennaro, Lucia Vadicamo
In this paper, we propose to extend the Surrogate Text Representation to specifically address a class of visual metric objects known as Vector of Locally Aggregated Descriptors (VLAD).
no code implementations • 14 Apr 2016 • Giuseppe Amato, Fabrizio Falchi, Claudio Gennaro
This poses obvious efficiency problems when using inverted files to perform efficient image matching.