Section: Partnerships and Cooperations

European Initiatives

FP7 & H2020 projects

FP7-PEOPLE-SHIVPRO

Participants : Olivier Le Meur, Zhi Liu.

• Title  : Saliency-aware High-resolution Video Processing.

• Research axis :   6.1.1 .

• Partners : Visting professor from Shanghai University.

• Funding : EC-FP7 MC-IIF International Incoming Fellowships (IIF).

• Period : 08/2012-07/2014

The SHIVPRO project has been supporting the visit of Dr. Z. Liu, from Beijing University in the team from August 2012 to August 2014. The objective of this project was to propose an efficient spatio-temporal saliency model to predict salient regions in High-Resolution (HR) videos, and fully exploit it to ease the design and improve the performance of HR video compression and retargeting applications. With the aim to overcome the drawbacks of existing saliency models, based on a multiscale region representation, the proposed model systematically realizes statistical model saliency measuring, intra-scale saliency modification, inter-scale saliency propagation and flexible incorporation of top-down information, to generate a novel saliency representation form with scalability, saliency tree, from which a multiscale saliency fusion scheme is used to derive high-quality saliency maps at various scales.