Web and Multimedia

ESPRESS

Smartphone identification based on on-board sensors.

2017-2018
Funded by: Fondazione Cassa di Risparmio Firenze
The main project’s aim is to study and develop a methodology to identify mobile devices through the analysis and combination of signals coming from the various on-board sensors, aiming to extract a smartphone fingerprint which is univocal and distinctive of one specific device.

Socializing the Semantic Gap

Image Tag Assignment, Refinement and Retrieval

2015-2016

We developed a comprehensive treatise of the three task of image tag assignment, refinement, and tag-based image retrieval. We introduce the functionality of tag relevance, i.e. estimating the relevance of a tag with respect to the visual content of a given image and its social context. A two-dimensional taxonomy to structure the growing literature and understand the ingredients of the main works is developed. A new experimental protocol is presented and eleven representative works are implemented and evaluated. Putting all this together, this work aims to provide an overview of the past and foster progress for the near future.

Image and Video Annotation by exploiting Social Media

Tagging and Retrieval of Social Media

2015-2016

The success of media sharing and social networks has led to the availability of extremely large quantities of images that are tagged by users. The need of methods to manage efficiently and effectively the combination of media and metadata poses significant challenges. In this project, we perform social media analysis and propose methods for automatic annotation of social images and videos.

MM-Forensics

Multimedia Forensics and Security

Multimedia forensics and Security project aims to introduce novel methodologies to support clue analysis and to provide an aid for making a decision about a crime by looking at a multimedia content as a digital clue (image and video).

Multimedia forensics deals with developing technological instruments operating in the absence of signatures or watermarks inserted in the image. These techniques basically allow the user to determine if a particular content has been tampered with or which was the acquisition device used.