VRT Medialab

Belgium

VRT Medialab

Belgium
SEARCH FILTERS
Time filter
Source Type

Messina A.,RAI Radiotelevision Italiana | De Sutter R.,VRT medialab | Sano M.,NHK Science and Technology | Friedland G.,International Computer Science Institute
MM'10 - Proceedings of the ACM Multimedia 2010 International Conference | Year: 2010

The third Workshop on Automated Information Extraction in Media Production (AIEMPro10) aims at fostering exchange of ideas and of practices between leading experts in research and leading actors in the media community, in order to catalyze the migration towards new ways of producing media content, aided by large scale introduction of tools for automated multimedia analysis and understanding. Furthermore, the workshop helps researchers in better understanding what are some real-life key requirements which would enable their scientific developments come into wider adoption.


De Sutter R.,Ghent University | Braeckman K.,VRT Medialab
SMPTE Motion Imaging Journal | Year: 2011

Soon, it will no longer be sufficient for only archivists to annotate audiovisual material. Not only is the number of archivists limited, but the time they spend on annotating one item is insufficient to create time-based and detailed descriptions about the content to make fully optimized video search possible. Furthermore, as a result of file-based production methods, we observe an accelerated increase in newly created audiovisual material that must be described. Fortunately, highquality feature extraction (FE) tools are increasingly being developed by research institutes. These tools examine the audiovisual essence and return particular information about the analyzed video, audio, or both streams. For example, the tools can automatically detect shot boundaries, detect and recognize faces and objects, and segment audio streams. As a result, they quickly and cheaply generate metadata that can be used for indexing and searching. In addition, they relieve archivists of the need to perform tedious, repetitive, but necessary low-added value tasks, such as identifying within an audio stream the speech and the music segments. Although most tools are not yet commercially offered, these solutions are expected to become available soon for broadcasters and media companies alike. This paper describes a solution for integrating such FE tools within the annotation workflow of a media company. This solution, in the form of an architecture and workflow, is scalable, extensible, and loosely coupled and has clear and easy-toimplement interfaces. As such, our architecture allows additional tools to be plugged in irrespective of the software and hardware used by the media company. By integrating FE tools within the workflow of the annotating audiovisual essence, more and better metadata can be created, allowing other tools to improve indexing, search, and retrieval of media material within audiovisual archives. © 2011 by SMPTE.


Mannens E.,Ghent University | Coppens S.,Ghent University | De Pessemier T.,Ghent University | Dacquin H.,VRT Medialab | And 3 more authors.
Multimedia Tools and Applications | Year: 2013

Today, people have only limited, valuable leisure time at their hands which they want to fill in as good as possible according to their own interests, whereas broadcasters want to produce and distribute news items as fast and targeted as possible. These (developing) news stories can be characterised as dynamic, chained, and distributed events in addition to which it is important to aggregate, link, enrich, recommend, and distribute these news event items as targeted as possible to the individual, interested user. In this paper, we show how personalised recommendation and distribution of news events, described using an RDF/OWL representation of the NewsML-G2 standard, can be enabled by automatically categorising and enriching news events metadata via smart indexing and linked open datasets available on the web of data. The recommendations - based on a global, aggregated profile, which also takes into account the (dis)likings of peer friends - are finally fed to the user via a personalised RSS feed. As such, the ultimate goal is to provide an open, user-friendly recommendation platform that harnesses the end-user with a tool to access useful news event information that goes beyond basic information retrieval. At the same time, we provide the (inter)national community with standardised mechanisms to describe/distribute news event and profile information. © 2011 Springer Science+Business Media, LLC.


De Sutter R.,VRT medialab | Matton M.,VRT medialab | Laukens N.,VRT medialab | Van Rijsselbergen D.,Ghent University | Van De Walle R.,Ghent University
Proceedings - 7th International Conference on Digital Content, Multimedia Technology and Its Applications, IDCTA 2011 | Year: 2011

As the consumer is becoming digital - i.e. he has personal mobile and always internet-connected devices allowing him to create a digital footprint anytime, anywhere - new opportunities arise for the "classic" broadcast industry to set up and maintain a direct relationship with their TV-viewers and radio-listeners. Until recently, a broadcaster had a one way connection with its customers, namely from the broadcaster, over the TV and radio distribution channel to the physical TV screen or radio set. Interaction was only possible after implementing and deploying expensive and hard-to-develop software on the set-top box. By employing web technology intelligently, a broadcaster can now more easily connect to its consumers and build a direct relationship. In this paper, we will discuss how to set up such a system and what the particular needs are in a broadcast context. We will use the second screen to collect data and enrich it in order to become beneficial information for the broadcasters and the advertisers. © 2011 AICIT.


Van Rijsselbergen D.,Ghent University | Poppe C.,Ghent University | Verwaest M.,VRT medialab | Mannens E.,Ghent University | Van De Walle R.,Ghent University
Multimedia Tools and Applications | Year: 2012

In order to provide audiences with a proper universal multimedia experience, all classes of media consumption devices, from high definition displays to mobile media players, must receive a product that is not only adapted to their capabilities and usage environments, but also conveys the semantics and cinematography behind the narrative in an optimal way. This paper introduces a semantic video adaptation system that incorporates the media adaptation process in the center of the drama production process. Producers, directors and other creative staff instruct the semantic adaptation system using common cinematographic terminology and vocabulary, thereby seamlessly extending the drama production process into the realm of content adaptation. The multitude of production metadata obtained from various steps in the production process provides a valuable context of narrative semantics that is exploited by the adaptation process. As such, high definition imagery can be intelligently adapted to smaller resolutions while optimally fulfilling the filmmaker's dramatic intentions with respect to the original narrative and obeying various rules of cinematographic grammar. © 2011 Springer Science+Business Media, LLC.


Coppens S.,Ghent University | Mannens E.,Ghent University | De Pessemier T.,Ghent University | Geebelen K.,Catholic University of Leuven | And 3 more authors.
Multimedia Tools and Applications | Year: 2012

Today, people have only limited, valuable spare time at their hands which they want to fill in as good as possible according to their interests. At the same time, cultural institutions are trying to attract interested communities to their carefully planned cultural programs. To distribute these cultural events to the right people, we developed a framework that will aggregate, enrich, recommend and distribute these events as targeted as possible. The aggregated events are published as Linked Open Data using an RDF/OWL representation of the EventsML-G2 standard. These event items are categorised and enriched via smart indexing and linked open datasets available on the Web of data. For recommending the events to the end-user, a global profile of the end-user is automatically constructed by aggregating his profile information from all user communities the user trusts and is registered to. This way, the recommendations take profile information into account from different communities, which has a detrimental effect on the recommendations. As such, the ultimate goal is to provide an open, user-friendly recommendation platform that harnesses the end-user with a tool to access useful event information that goes beyond basic information retrieval. At the same time, we provide the (inter)national cultural community with standardised mechanisms to describe/distribute event and profile information. © 2011 Springer Science+Business Media, LLC.


Ranaivoson H.,IBBT SMIT VUB | Donders K.,IBBT SMIT and IES VUB | Ballon P.,IBBT SMIT VUB | Sorgeloos H.,VRT medialab.
EuroITV'11 - Proceedings of the 9th European Interactive TV Conference | Year: 2011

We tackle the issue of innovation policy in the specific context of a small media sector, i.e. the Flemish one. The research question is twofold; firstly, asking which types of innovation should be supported by government; secondly, asking how to organise innovation policy in the broadcasting (and by extension media) sector. This study is based on a literature study, document analysis and several stakeholder interviews. © 2011 ACM.


Laukens N.,VRT Medialab
EBU Technical Review | Year: 2011

The Internet and worldwide web are continuously in motion. In the early days, pages were pure text although still images were incorporated fairly quickly, followed by moving pictures in the form of "Animated GIF" files. True video only became possible years later. Nowadays, video playback is ubiquitous on the web, but a smooth playback experience is not always guaranteed: long start-up times, inability to seek to an arbitrary point and re-buffering interruptions are no exceptions. In the last few years, however, new delivery techniques have been developed to resolve these issues, in particular "Adaptive Streaming" as described in this article.


De Sutter R.,VRT medialab | Nachtergaele L.,VRT medialab
EBU Technical Review | Year: 2011

Consumers are becoming more and more digital-oriented. Today, most of them have personal and always-connected mobile internet devices, thus allowing them to create a digital footprint anytime, anywhere. In tandem with this, new opportunities arise for the "classic" broadcast industry to set up and maintain a direct relationship with their TV viewers and radio listeners. Until recently, a broadcaster had a one-way connection to its customers... namely, over a TV or radio distribution channel to a physical TV screen or radio set. Interaction was only possible after implementing and deploying expensive and hardto-develop software on a set-top box. However, by employing web technology intelligently, a broadcaster can now more easily connect to its customers and build a direct relationship with them. In this article, we discuss how to set up such a system and what the particular needs are in a broadcast context. We use the second screen to collect data from our customers, and enrich it in order to acquire beneficial information for broadcasters and advertisers. We discuss a scalable architecture to process and handle this user information in real time, as well as for offline statistical analysis.


Matton M.,VRT Medialab | Braeckman K.,VRT Medialab
MM'11 - Proceedings of the 2011 ACM Multimedia Conference and Co-Located Workshops - AIEMPro 2011 Workshop, AIEMPro'11 | Year: 2011

Broadcast video retrieval is a key issue for media researchers looking for suitable media material in archives. Current media retrieval applications in use at VRT have proven to be a suboptimal solution. In this paper, we explain a novel search environment based on the combined metadata from multiple broadcast systems. Furthermore, we explain how speech recognition can facilitate unlocking the archive. This is illustrated by conducting experiments and measuring the keyword recognition rate, rather than the pure word error rate. We show that the keyword recognition rate is sufficient for efficient media retrieval in a search application. © 2011 ACM.

Loading VRT Medialab collaborators
Loading VRT Medialab collaborators