Patrick Le Callet
ABSTRACT
An extensive research work has been done in the last years to develop Visual Attention (VA) models for 2D, stereoscopic 3D images and videos or more recently for Virtual Reality and 360°. Reliable VA models are helpful in order to design efficient approaches for several applications, such as coding, streaming, foveated rendering, cinematography, movie editing, and Quality of Experience (QoE) evaluation. In this talk, I will review the current status on VA: advances and challenges from user study to modeling and benchmarking. A special focus will be dedicated to omnidirectional content. I will also illustrate how studying visual attention deployment of visual impaired people can help to improve VA computational modeling.
Index Terms
- The art of saliency modeling for multimedia applications
Recommendations
Mesh saliency
Research over the last decade has built a solid mathematical foundation for representation and analysis of 3D meshes in graphics and geometric modeling. Much of this work however does not explicitly incorporate models of low-level human visual ...
Mesh saliency
SIGGRAPH '05: ACM SIGGRAPH 2005 PapersResearch over the last decade has built a solid mathematical foundation for representation and analysis of 3D meshes in graphics and geometric modeling. Much of this work however does not explicitly incorporate models of low-level human visual ...
Visual saliency detection based on region descriptors and prior knowledge
Visual saliency detection not only plays a significant role, but it is also a challenging task in computer vision. In this paper we propose a new method for saliency detection. It incorporates visual features and spatial information with a guidance of ...
Comments