/RST-saliency

Here is the code for the paper 'Saliency Pattern Detection by Ranking Structured Trees' in ICCV 2017

Primary LanguageMATLABOtherNOASSERTION

RST-saliency

This is the source code for our paper in ICCV 2017: 'Saliency Pattern Detection by Ranking Structured Trees'. Lei Zhu, Haibin Ling, Jin Wu, Huiping Deng and Jin Liu.

Requirements

The project is build on MATLAB and is validated on both Windows 10 and Ubuntu 16.04 with CUDA 8. While in Windows system, visual studio 2013 is tested for generating the mex files.

Installation

  • Download dependencies from Baidu Yun or Google Drive. Please place both folders data and toolboxes into the root directory.

  • Compile MatConvNet in toolboxes if it is necessary. Please refer to the official guide for the instruction.

  • Put your own images in JPEG format into the folder test_samples and run the stript main_custom.m. The saliency maps can be found in folder test_samples_result.

Citation

If you find the code useful, please cite the following Bibtex code

@inproceedings{RSTsaliency-zhul,
	title = {Saliency Pattern Detection by Ranking Structured Trees},
	booktitle = {International Conference on Computer Vision},
	author = {Zhu, L. and Ling, H. and Wu, J. and Deng, H. and Liu, J.},
	month = {Oct.},
	year = {2017}
}

License

For academic usage, the code is released under the permissive BSD license. For any commercial purpose, please contact the authors.