Deep networks for saliency detection via local estimation and global search

@article{Wang2015DeepNF,
  title={Deep networks for saliency detection via local estimation and global search},
  author={Lijun Wang and Huchuan Lu and Xiang Ruan and Ming-Hsuan Yang},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={3183-3192}
}
This paper presents a saliency detection algorithm by integrating both local estimation and global search. In the local estimation stage, we detect local saliency by using a deep neural network (DNN-L) which learns local patch features to determine the saliency value of each pixel. The estimated local saliency maps are further refined by exploring the high level object concepts. In the global search stage, the local saliency map together with global contrast and geometric information are used… CONTINUE READING
Highly Influential
This paper has highly influenced 39 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 266 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 161 extracted citations

Computer Vision – ECCV 2018

Lecture Notes in Computer Science • 2018
View 18 Excerpts
Highly Influenced

Look, Perceive and Segment: Finding the Salient Objects in Images via Two-stream Fixation-Semantic CNNs

2017 IEEE International Conference on Computer Vision (ICCV) • 2017
View 8 Excerpts
Highly Influenced

Non-local Deep Features for Salient Object Detection

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 12 Excerpts
Highly Influenced

A shape preserving approach for salient object detection using convolutional neural networks

2016 23rd International Conference on Pattern Recognition (ICPR) • 2016
View 9 Excerpts
Highly Influenced

Visual Saliency Detection Based on Multiscale Deep CNN Features

IEEE Transactions on Image Processing • 2016
View 8 Excerpts
Highly Influenced

267 Citations

050100'14'15'16'17'18'19
Citations per Year
Semantic Scholar estimates that this publication has 267 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 43 references

Geodesic Object Proposals

View 5 Excerpts
Highly Influenced

The Secrets of Salient Object Segmentation

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 8 Excerpts
Highly Influenced

Hierarchical Saliency Detection

2013 IEEE Conference on Computer Vision and Pattern Recognition • 2013
View 4 Excerpts
Highly Influenced

Going deeper with convolutions

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2015
View 1 Excerpt

BING: Binarized Normed Gradients for Objectness Estimation at 300fps

2014 IEEE Conference on Computer Vision and Pattern Recognition • 2014
View 1 Excerpt

Similar Papers

Loading similar papers…