SAPIR Deliverable 3.2-3.5 - Feature Extraction Modules for Audio, Video, Music and Text
| Author | Aaron Kaplan |
| Domain | |
| Task | |
| Publisher | |
| Event | |
| Project | SAPIR |
| Dataset Used | |
| Published | 11/02/2009 |
| Copyright | The research leading to these results has received funding from the European Community’s Sixth Framework Programme (FP6) under grant agreement n° 45128 |
| DOI | |
Abstract
Work Package 3 is concerned w ith preparing multimedia documents for indexing and brow sing. The processing involved is different for each medium (video, still image, speech, text, and music), but in each case it means mapping a document to a specific representation supported by the index for that medium. A previous deliverable (D3.1) defined the representation format to be used. Deliverables D3.2, D3.3, D3.4, and D3.5 consist of softw are for mapping documents to that format. This report describes the softw are of all four deliverables and how it has been integrated into the SAPIR architecture.
Authors
Main Author(s) : Aaron Kaplan (Xerox)
Participants : Paolo Bolettieri, Fabrizio Falchi, Claudio Lucchese (CNR), Walter Allasia, Francesco Gallo (Eurix), Jonathan Mamou, Benjamin Sznajder (IBM), Riccardo Miotto, Nicola Orio (UPD), Caroline Brun, Jean-Marc Coursimault, Caroline Hagège, Mouna Kacimi (MPG)
Citations
Links
Link to Deliverable : http://www.sapir.eu/papers/deliverables/SAPIR-D3.2345-final.PDF Project Website : http://www.sapir.eu/
