VITALAS D3.3.1 State of the Art in Cross-Media Indexing
| http://vitalas.ercim.org/images/stories/pdf/d%203.1.1_v3.0.pdf | |
| Author | J. Tait & M. Abusalah |
| Domain | Cross-media indexing, Video indexing, Audio indexing, Image, Annotation, Supervised Machine Learning, Unsupervised Machine Learning,Dimensionality reduction. |
| Task | |
| Publisher | |
| Event | |
| Project | VITALAS |
| Dataset Used | |
| Published | 10 Sept 2007 |
| Copyright | The research leading to these results has received funding from the European Community’s Sixth Framework Programme (FP6) under grant agreement n° 045389 |
| DOI | |
Abstract
This deliverable overviews the state of the art in Cross-Media Indexing. A wide range of literature has been reviewed in the course of the associated workpackage. Media for which previous work is analysed in depth are still-image, video, audio, and text. The deliverable concludes that the most promising techniques all rest on supervised machine learning and this should be the focus of work in VITALAS.
Authors
J. Tait & M. Abusalah, University of Sunderland
List of Contributors − Mustafa Abusalah, University of Sunderland − Anastasios Delopoulos, CERTH-ITI − Arjen De Vries, CWI − Christos Diou, CERTH-ITI − Alexis Joly, INRIA − Panagiotis Panagiotopoulos, CERTH-ITI − Christos Papachristou, CERTH-ITI − Michael Oakes, University of Sunderland − Daniel Schneider, Fraunhofer IAIS − John Tait, University of Sunderland − Theodora Tsikrika, CWI − Thijs Westerveld, CWI
Citations
Links
Link to deliverable: http://vitalas.ercim.org/images/stories/pdf/d%203.1.1_v3.0.pdf Project website: http://vitalas.ercim.org/
