15th MuMe Work Meeting

imec, 25 februari 2010 (Only for members)
The goal of the work meetings is to have interactive sessions amongst the MuMe-Community members:
- Discussing recent evolutions of multimedia techniques.
- Discussing operational issues of the community.
- Discussing upcoming activities.
PLEASE NOTICE THAT THE FIRST PRESENTATION WILL BE STREAMED ON-LINE. WE KINDLY ASK YOU TO BE ON TIME
| 13:30 | Registration |
| Welcome/Coffee | |
| 13:55 | Welcome
Paul Six, Coordinator MuMe Community - IMEC |
| Welcome + introducing the streaming set-up. | |
| 14:00 | Bridging the gap between 3D computer graphics and video
Philippe Bekaert, Associate Professor - Univ. Hasselt - EDM |
| 3D computer graphics often looks unnatural and cartoon like. Although it is very well possible to create highly realistic computer graphics models and renderings, the cost of doing so is generally very large. Video technology on the other hand preserves realism by construction from scene to screen, but does not allow the fantastic freedom of computer graphics in creating or modifying models, or to navigate and interact in them. In this presentation, I will (re)discuss image and video based modeling and rendering in this light, and argue that we are only at the beginning of the development of a new visual medium with its own grammar and applications. | |
| 15:00 | NVision: building blocks for the next generation of image systems.
Francesco Pessolano - imec |
| In this presentation we will give an overview of our recent activities (and projects) in the domain of image- and video applications. We will also point out newly started R&D activities (eg, Hyperspectral imaging, Micro-mirror applications,... ). With some examples we will show how fundamental research creates real-world solutions. | |
| 15:40 | Break |
| Coffee | |
| 16:10 | Audio indexing for information retrieval.
Jean-Pierre Martens, Professor – UGent - ELIS |
| In order to make digital audio suitable for information retrieval, one employs automatic speech analysis and transcription (recognition) tools. The aim of the analysis tools is to perform a general-purpose indexing of the audio. These indexes help to control the transcription of the speech parts and to understand the structure and meaning of the audio scene. In this contribution some techniques for the automatic extraction of the type of audio (e.g. speech, applaus, music, ...), the type of speech (studio / telephone, read / spontaneous), the language being spoken and the ID of the speaker are being reviewed, and a life demo of one such a system that was intended for the indexing of TV-shows is presented. | |
| 16:50 | An end-to-end 3D TV chain: fundamentals, technologies and products
Matthias De Geyter - VRT-medialab |
| The main principles of 3D-TV will be presented in a structured way, including the state of the art of the technology, upcoming evolutions and the need for standards. We will touch on all aspects of an end-to-end 3D-TV chain: acquisition, compression, post production processing, distribution and displays. We will focus on the first generation 3D-TV (stereoscopic), but also discuss some next generation 3D technologies. | |
| 17:50 | Closing Networking drink with sandwiches |
Members please register your attendance via MuMe-Community@imec.be
If you are interested to join our Multimedia community, please check the informantion on "Membership" via New member?
| Date | Hour | Location | Street | City |
|---|---|---|---|---|
| 25 februari 2010 | 13.50 | imec | Kapeldreef 75 | Leuven |
