Bottom-up saliency model generation using superpixels

Polatsek, Patrik; Benešová, Wanda

doi:10.1145/2788539.2788557

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2015

2016

Publication Types

Select...

Other1

Article1

Relationship

Self Cite1

Independent1

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Superpixels have been already used in several application domains: salient object segmentation [9], object tracking [10], [11], salience detection [12], video analysis and segmentation [13], 3D reconstruction from video [14] etc.…”

Section: Introductionmentioning

confidence: 99%

Texture aware image error concealment

Uhlikova

Benešová

Polec

et al. 2015

IEEE EUROCON 2015 - International Conference on Computer as a Tool (EUROCON)

Self Cite

View full text Add to dashboard Cite

Error concealment is an error control technique capable of mitigating the error effects on multimedia using only the correctly received data. We introduce an efficient and highly scalable concealment algorithm for textured colour images. The lost area is restored by texture extrapolation from the surrounding regions logically associated on the superpixel level. With the proposed method also edges located in the lost area are retained. We validate results of the experiments against state of the art methods and demonstrate that our proposed algorithm performs much faster.

show abstract