Multimedia Tools and Applications – LIT

LIT: transcription, annotation, search and visualization tools for the Lexicon of the Italian Television

LIT (Lexicon of the Italian Television) is a project conceived by the Accademia della Crusca, the leading research institution on the Italian language, in collaboration with CLIEO (Center for theoretical and historical Linguistics: Italian, European and Oriental languages), with the aim of studying frequencies of the Italian vocabulary used in television. Approximately 170 hours of random television recordings acquired from the national broadcaster RAI (Italian Radio Television) during the year 2006 have been used to create the corpus of transcriptions. The principal outcome of the project is the design and implementation of an interactive system which combines a web-based video transcription and annotation tool, a full featured search engine, and a web application for data visualization with text-video syncing. Furthermore, the project is currently under deployment as a module of the larger national research funding FIRB 2009 VIVIT (Fondo di Investimento per la Ricerca di Base, Vivi l'Italiano), which will integrate its achievements and results within a semantic web infrastructure.

Springer, Multimedia Tools and Applications

ACM Multimedia 2010 – Shawbak

Full title: Natural Interaction for Cultural Heritage: the archaeological site of Shawbak

Abstract: One of the most interesting issues in the field of cultural heritage is the adoption of multimedia systems for the visualization and organization of information. In this paper we present a natural interaction based system designed to represent multimedia contents related to the archaeological site of Shawbak, situated in the Petra region of Jordan. Contents are composed of texts, images and videos showing and explaining the archeological site areas and the history of the castle. This system was installed at the Limonaia di Palazzo Pitti (Italy) for the archeological exhibition called "From Petra to Shawbak".

Link to ACM portal reference.


ACM Multimedia 2009 – Sirio

In this technical demonstration we show a web video search engine based on ontologies, the Sirio system, that has been developed within the EU VidiVideo project. The goal of the system is to provide a search engine for videos for both technical and non-technical users. In fact, the system has different interfaces that permit different query modalities: free-text, natural language, graphical composition of con- cepts using boolean and temporal relations and query by visual example. In addition, the ontology structure is ex- ploited to encode semantic relations between concepts per- mitting, for example, to expand queries to synonyms and concept specializations.

Link to ACM Portal reference.

ACM Multimedia 2009 – Arneb

In this technical demonstration we show the current version of Arneb, a web-based system for manual annotation of videos, developed within the EU VidiVideo project. This tool has been developed with the aim of creating ground truth annotations, that can be used for training and evalu- ating automatic video annotation systems. Annotations can be exported to MPEG-7 and OWL ontologies. The system has been developed according to the Rich Internet Applica- tion paradigm, allowing collaborative web-based annotation.

Link to ACM Portal reference.

EVA 2009 – Natural Interaction

This paper presents the media interaction systems implemented at the Mont'Alfonso Fortress, close to Castelnuovo Garfagnana (Lucca). The stronghold was built at the end of the 16th century and after being abandoned for decades it was recently submitted to a complete restoration. A multimedia environment, made of large projections, was developed in one of the buildings inside the fortress. Users can interact with natural body gestures: the multimedia contents of two tables are driven by user's hands, while projections on walls and floor are activated by motion detection. All the sensing is made using near-IR cameras.

Download PDF


EVA 2006 - Cruscle search engine

This paper presents the advanced search tecniques implemented for the Accademia della Crusca on-line vocabularies. The five vocabularies represent the origin and evolution of the Italian language during the last centuries. They have been completely transcripted and annotated in a standard XML/TEI format. The transcription has been indexed with a complex structure that allows advanced search queries, including: full text query, context and micro- context queries, case sensitiveness, accented characters, search of word roots and punctuation marks. The search algorithms are based on the open source indexing and search engine Apache Lucene with heavy modifications.

Download PDF


IEEE Multimedia 2005 - Natural Interfaces

The authors present a multimedia system that really works in a cultural public space. Indeed, if you go to Florence and visit the museum of Palazzo Medici Riccardi, you might see a queue of worldwidetourists waiting for their turn to play with a digital version of the famous fresco The Journey of the Magi, appearing on two large screens. Visitors stand in front of the screens and point with their hands to the part of the painting theyýre interested in. Two cameras grab this point and analgorithm calculates the exact part of the painting the person selected. In response to the pointing, an audio response gives information on the subjects or objects. Visitors seem to deeply enjoy theirinteraction with the system, which does feel natural. Visitors wear no special equipment and use no complex hardware; the fresco is extremely well displayed, and typically the information is precise and interesting, with different levels of information available.

Link to ACM Portal reference.


ICPR 2004 - Motion capture

In this paper a composite framework for collaborative working is presented. The framework includes real-time motion tracking based on computer vision from standard webcams situated at different locations, data transmission and real-time animation of 3D avatars in a virtual world. Motion tracking is obtained without using markers, with weak constraints on users' clothes and environment lighting. It is based on a model fitting process that compares the 2D processed images supplied by cameras with a set of artificially generated views of a human model.

Link to ACM Portal reference.