F
Fabrizio Falchi
Researcher at National Research Council
Publications - 170
Citations - 2657
Fabrizio Falchi is an academic researcher from National Research Council. The author has contributed to research in topics: Image retrieval & Deep learning. The author has an hindex of 20, co-authored 149 publications receiving 1753 citations. Previous affiliations of Fabrizio Falchi include Istituto di Scienza e Tecnologie dell'Informazione.
Papers
More filters
Journal ArticleDOI
Deep learning for decentralized parking lot occupancy detection
TL;DR: The paper proposes a decentralized and efficient solution for visual parking lot occupancy detection based on a deep Convolutional Neural Network specifically designed for smart cameras, and provides a new training/validation dataset for parking occupancy detection.
Posted Content
CoPhIR: a Test Collection for Content-Based Image Retrieval
Paolo Bolettieri,Andrea Esuli,Fabrizio Falchi,Claudio Lucchese,Raffaele Perego,Tommaso Piccioli,Fausto Rabitti +6 more
TL;DR: The experience in building a test collection of 100 million images, with the corresponding descriptive features, to be used in experimenting new scalable techniques for similarity searching, and comparing their results is reported on.
Proceedings ArticleDOI
Car parking occupancy detection using smart camera networks and Deep Learning
TL;DR: This paper presents an approach for real-time car parking occupancy detection that uses a Convolutional Neural Network (CNN) classifier running on-board of a smart camera with limited resources that is effective and robust to light condition changes, presence of shadows, and partial occlusions.
Journal ArticleDOI
Building a web-scale image similarity search system
Michal Batko,Fabrizio Falchi,Claudio Lucchese,David Novak,Raffaele Perego,Fausto Rabitti,Jan Sedmidubsky,Pavel Zezula +7 more
TL;DR: The experience in building an experimental similarity search system on a test collection of more than 50 million images and the performance of this technology and its evolvement as the data volume grows by three orders of magnitude is studied.
Proceedings ArticleDOI
Cross-Media Learning for Image Sentiment Analysis in the Wild
Lucia Vadicamo,Fabio Carrara,Andrea Cimino,Stefano Cresci,Felice Dell'Orletta,Fabrizio Falchi,Maurizio Tesconi +6 more
TL;DR: This empirical study shows that although the text associated to each image is often noisy and weakly correlated with the image content, it can be profitably exploited to train a deep Convolutional Neural Network that effectively predicts the sentiment polarity of previously unseen images.