Inhalt des Dokuments
zur Navigation
Marie-Neige Garcia
- © Copyright??
Marie-Neige Garcia is now with the Fachgebiet Assessment of IP-based Applications.
Research Field: - Quality and Usability Research Topics: - Video and Audio-Visual Quality Assessment
- Quality modeling
Biography Since 2006: PhD Student at Technische Universität Berlin / Deutsche Telekom Laboratories 2004-2006: Project manager at ELDA (Evaluation and Language Resources Distribution Agency) , Speech evaluation department - Paris, France
- Project manager in the EVALDA/EvaSy campaign (Evaluation of speech synthesis systems in French)
- In charge of the evaluation of Text-to-speech systems in the European project TC-STAR (speech-to-speech translation)
- In charge of the evaluation of video technologies in the project CHIL (Pervasive Interaction Computing)
2003: Master’s Degree in Engineering at ISEP (Electronics Superior Institute of Paris); areas of study: informatics, telecommunications, electronics
Address Quality and Usability Lab
Deutsche Telekom Laboratories
TU Berlin
Ernst-Reuter-Platz 7
D-10587 Berlin, Germany
Publications
| Zitatschlüssel | argyropoulos2013a |
|---|---|
| Autor | Argyropoulos, Savvas and Garcia, Marie-Neige and List, David and Schleicher, Robert and Raake, Alexander |
| Buchtitel | Int. Workshop on Video Processing and Quality Metrics (VPQM) |
| Jahr | 2013 |
| Monat | jan |
| Zusammenfassung | In this paper, a novel no-reference method to predict the impact of packet losses in video sequences on visual attention is proposed. Initially, the results of a subjective eye-tracking experiment are analyzed to determine whether the artefacts caused by network degradations result in abrupt saliency changes. Then, the proposed method employs existing objective visual attention models to compute the saliency maps of the individual frames. Subsequently, the temporal consistency of the saliency maps is investigated and correlated with the error propagation pattern that results from the packet losses to predict visual saliency changes in a rule-based approach. Experimental results on a proprietary database are presented to demonstrate the validity of the proposed method. |