Italia
Informazioni di contatto
52.312 follower
Oltre 500 collegamenti
Informazioni
Articoli di Alessandro
-
Re-thinking Face Detection in the Covid-19 age
Re-thinking Face Detection in the Covid-19 age
Di Alessandro Ferrari
-
Introduzione al tracking di oggetti | Il paradigma di osservazione-propagazione
Introduzione al tracking di oggetti | Il paradigma di osservazione-propagazione
Di Alessandro Ferrari
-
BOOST THE WORLD PROJECT for fast object detection
BOOST THE WORLD PROJECT for fast object detection
Di Alessandro Ferrari
Esperienza e formazione
Pubblicazioni
-
TINYCD: A (Not So) Deep Learning Model For Change Detection
👉 In this work we propose a novel model, called TinyCD, demonstrating to be both lightweight and effective, able to achieve performances comparable or even superior to the current state of the art with 13-150X fewer parameters. In our approach we have exploited the importance of low-level features to compare images. To do this, we use only few backbone blocks. This strategy allow us to keep the number of network parameters low. To compose the features extracted from the two images, we…
👉 In this work we propose a novel model, called TinyCD, demonstrating to be both lightweight and effective, able to achieve performances comparable or even superior to the current state of the art with 13-150X fewer parameters. In our approach we have exploited the importance of low-level features to compare images. To do this, we use only few backbone blocks. This strategy allow us to keep the number of network parameters low. To compose the features extracted from the two images, we introduce a novel, economical in terms of parameters, mixing block capable of cross correlating features in both space and time domains. Finally, to fully exploit the information contained in the computed features, we define the PW-MLP block able to perform a pixel wise classification.
-
Boosted Tracking in Video
Image Analysis and Processing – ICIAP 2009. Lecture Notes in Computer Science.
👉 A probabilistic interpretation of the output provided by a cascade of boosted classifiers can be exploited for Bayesian tracking in video streams. In particular, real-time face and body detection can be achieved by relying on such a Bayesian framework. Results show that such integrated approach is appealing with respect both to robustness and computational efficiency.
-
Real-Time Probabilistic Tracking of Faces in Video
ICIAP 2009: Image Analysis and Processing
👉 Real-time face detection and tracking in video can be achieved by relying on a Bayesian approach realized in a multi-threaded architecture. To this end we propose a probabilistic interpretation of the output provided by a cascade of AdaBoost classifiers. Results show that such integrated approach is appealing with respect either to robustness and computational efficiency.
Riconoscimenti e premi
-
🏆"Net economy ideas" award
Università Commerciale Luigi Bocconi - Milano
-
🏆Scholarship (highest grade point average)
ITIS Galileo Galilei - Milano
Lingue
-
Italian
Conoscenza madrelingua o bilingue
-
English
Conoscenza professionale
-
Italiano
Conoscenza madrelingua o bilingue
-
Inglese
Conoscenza professionale completa
Referenze ricevute
20 persone hanno scritto una referenza per Alessandro
Iscriviti ora per vedereAltri profili simili
Altre persone che si chiamano Alessandro Ferrari in Italia
Su LinkedIn ci sono altre 493 persone che si chiamano Alessandro Ferrari in Italia
Vedi altre persone che si chiamano Alessandro Ferrari