ViSTA-TV

ViSTA-TV - Video Stream Analytics for Viewers in the TV Industry

Coordinatore	UNIVERSITAET ZUERICH    more  Organization address contact info Titolo: Prof. Nome: Abraham Cognome: Bernstein Email: send email Telefono: +41 44 635 4579 Fax: +41 44 635 68 09
Nazionalità Coordinatore	Switzerland [CH]
Totale costo	2˙605˙896 €
EC contributo	1˙995˙000 €
Programma	FP7-ICT Specific Programme "Cooperation": Information and communication technologies
Code Call	FP7-ICT-2011-SME-DCL
Funding Scheme	CP
Anno di inizio	2012
Periodo (anno-mese-giorno)	2012-06-01   -   2014-05-31

 Partecipanti

#	participant	country	role	EC contrib. [€]
1	UNIVERSITAET ZUERICH	CH	coordinator	0.00
2	BRITISH BROADCASTING CORPORATION  Organization address address: PORTLAND PLACE BROADCASTING HOUSE city: LONDON contact info Titolo: Ms. Nome: Hélène Cognome: Waters Email: send email Telefono: +44 1604 737 675 Fax: +44 1604 737 624	UK (LONDON)	participant	0.00
3	EIDGENOESSISCHE TECHNISCHE HOCHSCHULE ZURICH  Organization address address: Raemistrasse 101 city: ZUERICH contact info Titolo: Ms. Nome: Agatha Cognome: Keller Email: send email Telefono: +41 44 634 53 50	CH (ZUERICH)	participant	0.00
4	RAPIDMINER GMBH  Organization address address: STOCKUMER STRASSE 475 city: DORTMUND contact info Titolo: Dr. Nome: Ingo Cognome: Mierswa Email: send email Telefono: +49 231 425 786 90	DE (DORTMUND)	participant	0.00
5	STICHTING VU-VUMC  Organization address address: DE BOELELAAN 1105 city: AMSTERDAM contact info Titolo: Dr. Nome: Yvonne Cognome: Kops Email: send email Telefono: +31 20 5987500	NL (AMSTERDAM)	participant	0.00
6	TECHNISCHE UNIVERSITAET DORTMUND  Organization address address: AUGUST-SCHMIDT-STRASSE 4 city: DORTMUND contact info Titolo: Mr. Nome: Michael Cognome: Lohmeier Email: send email Telefono: 492318000000 Fax: 492318000000	DE (DORTMUND)	participant	0.00
7	ZATTOO EUROPA AG  Organization address address: EGGBUHLSTRASSE 28 city: ZURICH contact info Titolo: Mr. Nome: Beat Cognome: Knecht Email: send email Telefono: +41 43 500 2101	CH (ZURICH)	participant	0.00

Mappa

 Word cloud

Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.

 Obiettivo del progetto (Objective)

Live video content is increasingly consumed over IP networks in addition to traditional broadcasting. The move to IP provides a huge opportunity to discover what people are watching in much greater breadth and depth than currently possible through interviews or set-top box based data gathering by rating organizations, because it allows direct analysis of consumer behavior via the logs they produce. The ViSTA-TV project proposes to gather consumers' anonymized viewing behavior and the actual video streams from broadcasters/IPTV-transmitters to combine them with enhanced electronic program guide information as the input for a holistic live-stream data mining analysis: the basis for an SME-driven market-place for TV viewing-behavior information. First, ViSTA-TV will employ the gathered information via a stream-analytics process to generate a high-quality linked open dataset (LOD) describing live TV programming. Second, combining the LOD with the behavioral information gathered, ViSTA-TV will be in the position to provide highly accurate market research information about viewing behavior that can be used for a variety of analyses of high interest to all participants in the TV-industry. This generates a novel, SME-driven market place for TV viewing-behavior data and analyses. Third, to gather anonymized behavioral information about viewers not using our IPTV-streams ViSTA-TV will employ the gathered information to build a recommendation service that exploits both usage information and personalized feature extraction in conjunction with existing meta-information to provide real-time viewing recommendations. Commercially, the revenues gathered in the market research activity will cross-subsidize the production of the open-sourced LOD stream. These results are made possible by scientific progress in data-stream mining consisting of advances in (1) data mining for tagging, recommendations, and behavioral analyses and (2) temporal/probabilistic RDF-triple stream processing.