Search Results for author:
Found 46 papers, 25 papers with code
Is CLIP the main roadblock for fine-grained open-world perception?
Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training.
Deepfake Detection without Deepfakes: Generalization via Synthetic Frequency Patterns Injection
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.
The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding
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.
Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey
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.
Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey
Recently emerged technologies based on Deep Learning (DL) achieved outstanding results on a variety of tasks in the field of Artificial Intelligence (AI).
Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language
Due to recent advances in pose-estimation methods, human motion can be extracted from a common video in the form of 3D skeleton sequences.
The Emotions of the Crowd: Learning Image Sentiment from Tweets via Cross-modal Distillation
Trends and opinion mining in social media increasingly focus on novel interactions involving visual media, like images and short videos, in addition to text.
Detecting Images Generated by Diffusers
This paper explores the task of detecting images generated by text-to-image diffusion models.
MINTIME: Multi-Identity Size-Invariant Video Deepfake Detection
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
Deep learning for structural health monitoring: An application to heritage structures
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.
A Spatio-Temporal Attentive Network for Video-Based Crowd Counting
Automatic people counting from images has recently drawn attention for urban monitoring in modern Smart Cities due to the ubiquity of surveillance camera networks.
ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval
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
Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection
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.
Transformer-Based Multi-modal Proposal and Re-Rank for Wikipedia Image-Caption Matching
With the increased accessibility of web and online encyclopedias, the amount of data to manage is constantly increasing.
Deep Features for CBIR with Scarce Data using Hebbian Learning
Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR).
MOBDrone: a Drone Video Dataset for Man OverBoard Rescue
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).
Recurrent Vision Transformer for Solving Visual Reasoning Problems
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.
Generative Adversarial Networks for Astronomical Images Generation
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.
AIMH at SemEval-2021 Task 6: Multimodal Classification Using an Ensemble of Transformer Models
This paper describes the system used by the AIMH Team to approach the SemEval Task 6.
Combining EfficientNet and Vision Transformers for Video Deepfake Detection
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)
A Leap among Quantum Computing and Quantum Neural Networks: A Survey
In recent years, Quantum Computing witnessed massive improvements in terms of available resources and algorithms development.
Multi-Camera Vehicle Counting Using Edge-AI
This paper presents a novel solution to automatically count vehicles in a parking lot using images captured by smart cameras.
Towards Efficient Cross-Modal Visual Textual Retrieval using Transformer-Encoder Deep Features
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).
MAFER: a Multi-resolution Approach to Facial Expression Recognition
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.
Hebbian Semi-Supervised Learning in a Sample Efficiency Setting
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).
A Multi-resolution Approach to Expression Recognition in the Wild
Facial expressions play a fundamental role in human communication.
Facial Expression Recognition
Facial Expression Recognition (FER)
Solving the Same-Different Task with Convolutional Neural Networks
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.
Expression Recognition Analysis in the Wild
The main goal of this work is to define a baseline for a novel method we are going to propose in the near future.
Training Convolutional Neural Networks With Hebbian Principal Component Analysis
In particular, it has been shown that Hebbian learning can be used for training the lower or the higher layers of a neural network.
Assessing Pattern Recognition Performance of Neuronal Cultures through Accurate Simulation
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
MOCCA: Multi-Layer One-Class ClassificAtion for Anomaly Detection
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
Combining GANs and AutoEncoders for Efficient Anomaly Detection
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.
Fine-grained Visual Textual Alignment for Cross-Modal Retrieval using Transformer Encoders
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
The VISIONE Video Search System: Exploiting Off-the-Shelf Text Search Engines for Large-Scale Video Retrieval
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.
TweepFake: about Detecting Deepfake Tweets
To prevent this, it is crucial to develop deepfake social media messages detection systems.
Automatic Pass Annotation from Soccer VideoStreams Based on Object Detection and LSTM
In this paper, we describe PassNet, a method to recognize the most frequent events in soccer, i. e., passes, from video streams.
Transformer Reasoning Network for Image-Text Matching and Retrieval
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.
Virtual to Real adaptation of Pedestrian Detectors
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.
Detection of Face Recognition Adversarial Attacks
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.
Cross-Resolution Learning for Face Recognition
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.
AI in the media and creative industries
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.
Exploring epoch-dependent stochastic residual networks
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.
Aggregating Binary Local Descriptors for Image Retrieval
Content-Based Image Retrieval based on local features is computationally expensive because of the complexity of both extraction and matching of local feature.
Picture It In Your Mind: Generating High Level Visual Representations From Textual Descriptions
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.
Using Apache Lucene to Search Vector of Locally Aggregated Descriptors
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).
On Reducing the Number of Visual Words in the Bag-of-Features Representation
This poses obvious efficiency problems when using inverted files to perform efficient image matching.
