02 October 2014
Master Degree in:
COMPUTER ENGINEERING - Data Engineering (Rating 110/110 cum laude)from POLITECNICO DI MILANO
26 September 2012
Bachelor Degree in:
COMPUTER ENGINEERING (Rating 110/110 cum laude)from POLITECNICO DI MILANO
EXPERT Technician (PERITO CAPOTECNICO) in COMPUTER SCIENCE (Rating 100/100)from ISTITUTO TECNICO IND.LE MAGISTRI CUMACINI (COMO - ITALY)
From September 2012 to September 2014
ProgeCAD s.r.l. COMO ITALY
Job: Software Developer
ProgeCAD s.r.l. is a company engaged in the IT industry, in particular in the field of CAD/CAM Software solutions.
At this company I am involved in the production and maintenance of add-on for progeCAD.
From October 2013 to March 2014
Politecnico di Milano COMO ITALY
Job: Teaching Assistant
The Politecnico di Milano is the largest technical university in Italy
During this period I've held the role of Teaching Assistan for the course of Fondamenti di Informatica (IT Basics)
From October 2009 to August 2012
ProgeSOFT s.a.s. COMO ITALY
Job: Software Developer Apprentice
ProgeSOFT s.r.l. is a company engaged in the IT industry, in particular in the field of CAD/CAM Software solutions.
At this company I have been involved in the production and maintenance of add-on for progeCAD.
From September 2008 to June 2009
BetaCAD s.r.l. COMO ITALY
Job: Software Developer
BetaCAD s.r.l. is a company engaged in the IT industry, in particular in the field of Electrical and Furniture CAD/CAM Software solutions.
At this company I have been involved in the production and maintenance of add-on for AutoCAD and EleCAE/ElettraCAD.
.NET Framework, MFC, Win32 API, QT, wxWidgets, C++ STL
Platforms: node.js, play
Frameworks: express, JQuery, Bootstrap, Polymer
20 May 2015
C. Bernaschina, I. Catallo, P. Fraternali, D. Martinenghi, M. TagliasacchiWe present Champagne, a web tool for the execution of crowdsourcing campaigns. Through Champagne, task requesters can model crowdsourcing campaigns as a sequence of choices regarding different, independent crowdsourcing design decisions. Such decisions include, e.g., the possibility of qualifying some workers as expert reviewers, or of combining different quality assurance techniques to be used during campaign execution. In this regard, a walkthrough example showcasing the capabilities of the platform is reported. Moreover, we show that our modular approach in the design of campaigns overcomes many of the limitations exposed by the major platforms available in the market.
02 October 2014
Master Degree Thesis
C. BernaschinaIn this work we present an abstract, reusable and context-independent algorithm for annotation aggregation. This algorithm can be instantiated by defining context-dependent operations on the specific annotation type. We analyze the state of the art in annotation aggregation and identify the main problems and propose solutions in order to deal with them. We analyze common annotation types an propose instantiations of the algorithm in this cases. Tests performed on both synthetic and real datasets revealed a reduction up to 70%, with respect to standard approaches, in the number of required annotations given a predefined accuracy level.
01 April 2014
C. Bernaschina, P. Fraternali, L. Galli, D. Martinenghi, M. TagliasacchiThe possibility of assigning labels to localized regions in an image enables flexible image retrieval paradigms. However, the process of automatically segmenting and tagging images is notoriously hard, due to the presence of occlusions, noise, challenging illumination conditions, background clutter, etc. For this reason, human computation has recently emerged as a viable alternative when computer vision algorithms fail to provide a satisfactory answer. For example, Games with a purpose (GWAP) represent a powerful crowdsourcing mechanism to collect implicit annotations from human players. In this paper we consider the problem of aggregating the gaming tracks collected by a GWAP we developed to solve challenging instances of image segmentation problems. In particular we consider the existence of malicious players, who might try to fool the rules of the game to achieve higher rewards. The proposed solution can automatically estimate the reliability of human players, thus identifying cheaters. This information is exploited to aggregate the gaming tracks, thus significantly improving the image segmentation result and the quality of local image annotations.