Home

Awesome

Deep Networks for Saliency Detection via Local Estimation and Global Search

Introduction

LEGS is a state-of-the-art salient object detection system which utilizes deep networks to combine local estimation and global search. This pachage contains the source code to reproduce the experimental results of LEGS reported in the CVPR 2015 paper

Citing LEGS

If you find LEGS useful in your research, please consider to cite our paper:

 @inproceedings{ wang2015deep,
    title={Deep Networks for Saliency Detection via Local Estimation and Global Search},
    author={Wang, Lijun and Lu, Huchuan and Ruan, Xiang and Yang, Ming-Hsuan},
    booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
    pages={3183--3192},
    year={2015}
 }

Dependencies

How to Run

Note

Contact

wlj@mail.dlut.edu.cn

Reference

[R1] Jia Y, Shelhamer E, Donahue J, et al. Caffe: Convolutional architecture for fast feature embedding, ACM International Conference on Multimedia, 2014.

[R2] Li H, Zhao R, Wang X. Highly efficient forward and backward propagation of convolutional neural networks for pixelwise classification. arXiv preprint, 2014.

[R3] Krähenbühl P, Koltun V. Geodesic object proposa, ECCV 2014.