HPC is a foundation uniting 51 interdisciplinary public and private organizations, driving substantial and sustainable innovations across various fields, from basic research to computational and experimental sciences, supporting education, and advocating responsible data management for open science.
OnFoods is a foundation that brings together, coordinates and amplifies the work of 26 public and private organisations, leaders in scientific research and sustainable innovation of food systems.
Progetto E4S – ENERGY FOR SAFETY: Sistema integrato per la sicurezza della persona ed il …
We designed an adaptive color constancy algorithm that, exploiting the skin regions found in faces, is able to estimate and correct the scene illumination
ArabCeleb: Speaker Recognition in Arabic In this paper we present ArabCeleb, a dataset collected in …
Color constancy algorithms are typically evaluated with a statistical analysis of the recovery angular error …
Sabato 1 ottobre 2016 abbiamo partecipato al Meet Me Tonight 2016. I visitatori dello stand …
In this project we shall consider the problem of deploying attention to subsets of the video streams for collating the most relevant data and information of interest related to a given task. We formalize this monitoring problem as a foraging problem.
We create a new dataset composed of 120,000 images of 50 diverse food categories. The images are accurately annotated with pixel-wise annotations. The dataset is augmented with the same 5,000 images but rendered under different acquisition distortions that comprise illuminant change, JPEG compression, Gaussian noise, and Gaussian blur.
A multi-touch tabletop system for browsing image databases, conceived for museums and art gallery exhibitions. The system exploits an innovative image browsing paradigm and image retrieval functionalities to perform natural and intuitive user interaction.
Visual complexity perception plays an important role in the fields of both psychology and computer vision. We investigate image complexity of different kind of stimuli. We perform different types of psycho-physical experiments and correlate subjective data with objective measures.
We present an extensive evaluation of visual descriptors for the content-based retrieval of remote sensing (RS) images. The evaluation includes global, local, and Convolutional Neural Network (CNNs) features coupled with four different Content-Based Image Retrieval schemes.
This research focuses on the exploration of the most widely adopted libraries specifically designed for data augmentation in computer vision tasks. Through a curated taxonomy, we present an organized classification of different approaches employed by these libraries, along with accompanying application examples.
In this work we investigate the use of deep learning for distortion-generic blind image quality assessment.
Try the demo.
In this project we present a method for logo recognition based on deep learning. Our recognition …
In this project we use deep learning with the aim of automatically finding products in grocery store shelves.
Structure from Motion (SfM) is a pipeline that allows three-dimensional reconstruction starting from a collection of images. We also propose an evaluation procedure that stresses the SfM pipelines using real dataset acquired with high-end devices as well as realistic synthetic dataset. To this end, we publish a dataset to be used in the evaluation.
Life expectancy keeps growing and, among elderly people, accidental falls occur frequently. A system able to promptly detect falls would help in reducing the injuries that a fall could cause.
We propose a network architecture to perform efficient scene understanding. This work presents three main …
Food524DB is the largest publicly available food dataset with 524 food classes and 247,636 images by merging food classes from existing datasets in the state of the art. This database can be used for food recognition. The database is composed of 247,636 images belonging to 524 food categories.
Automatic food recognition is an important task to support the users in their daily dietary monitoring and to keep tracks of their food consumption. We have designed datasets and algorithms for automatic dietary monitoring of canteen customers based on robust computer vision techniques.
We introduce a new dataset containing fruits and vegetables in different states. We experiment with most common Convolutional Neural Network (CNN) architectures on three different recognition tasks: food categories, food states, and joint food and states.
Food-475 database is one of the largest publicly available food database with 475 food classes and 247,636 images obtained by merging four publicly available food databases.
We address the task of classifying car images at multiple levels of detail, ranging from …
The annotation of image and video data of large datasets is a fundamental task in multimedia information retrieval and computer vision applications. In order to support the users during the image and video annotation process, several software tools have been developed to provide them with a graphical environment which helps drawing object contours, handling tracking information and specifying object metadata.
In this paper we present a three-stage method for the estimation of the color of the …
In this paper we investigate the use of a deep Convolutional Neural Network (CNN) to predict …
In this work we present an algorithm for the automatic detection of the image orientation that relies on the image content as described by Local Binary Patterns (LBP).
Image quality assessment (IQA) is a multidimensional research problem and an active and evolving research …
We have developed algorithms for image similarity computation and image representation that can be used in content based image retrieval systems as well as for image understanding in classification tasks.
This work aims at automatically recognizing sequences of complex karate movements and giving a measure …
This work introduces a new method for face verification across large age gaps and also a dataset containing variations of age in the wild, the Large Age-Gap (LAG) dataset, with images ranging from child/young to adult/old.
A review of existing methods for local visual detectors and descriptors.
We propose a strategy for land use classification which exploits Multiple Kernel Learning (MKL) to automatically determine a suitable combination of a set of features without requiring any heuristic knowledge about the classification task.
Assisted living technologies can be of great importance for taking care of elderly people and helping them to live independently. We propose a monitoring system designed to be as unobtrusive as possible, by exploiting computer vision techniques and visual sensors such as RGB cameras.
In this project we propose a new deep multibranch neural network to solve the tasks …
The Raw Food Texture database (RawFooT) has been specially designed to investigate the robustness of descriptors and classification methods with respect to variations in the lighting conditions, with a particular focus on variations in the color of the illuminant.
Semantic segmentation architectures are mainly built upon an encoder-decoder structure. These models perform subsequent downsampling …
In this work a local optimization-based method that is able to recover the reflectance spectra …
Estimation of image saliency can be defined as the task of assigning different levels of …
Printer characterization usually requires a large number of printer inputs and corresponding color measurements of …
We have developed the iVAT: an interactive Video Annotation Tool. It supports manual, semi-automatic and automatic annotations through the interaction of the user with various detection algorithms.
In this work we address the problem of optimal sensor placement for a given region and task. An important issue in designing sensor arrays is the appropriate placement of the sensors such that they achieve a predefined goal.
In this work we propose HR-Dehazer, a novel and accurate method for image dehazing. An …
We present a fully automated approach for smile detection. Faces are detected using a multi-view …
T1K+: a database for benchmarking color texture classification and retrieval methods In this paper we …
Computational color constancy algorithms are commonly evaluated only through angular error analysis on annotated datasets …
U-WeAr: User Recognition on Wearable Devices through Arm Gesture The use of wearable devices equipped …