Caffe Implementation (v1) for
By Hongmei Song and Wenguan Wang and Sanyuan Zhao and Jianbing Shen and Kin-Man Lam
===========================================================================
2019/10: Results on DAVIS17 val and test sets are added (instance-level video object segmentation)
========================================================================
Please install our modified caffe first. Download our model (https://drive.google.com/open?id=1vsGV31gfYA48j8usoRjTtfn-IpBosGFH) and put it in 'model' folder. (Baidu disk link: https://pan.baidu.com/s/1s8m9Mo9XLSHt0hVdEBa4ww&shfl=sharepset#list/path=%2F)
Then edit paths in 'test_davis.py'.
Finally, run 'test_davis.py'.
========================================================================
The saliency and segmentation results (on the test sets of DAVIS16 and FBMS) can also be found at https://drive.google.com/open?id=1oOeoDAkxInOL_lKvgaSlnjO_6OLhL2Ew (Baidu disk link: https://pan.baidu.com/s/1s8m9Mo9XLSHt0hVdEBa4ww&shfl=sharepset#list/path=%2F)
The IOU score of the FBMS-test set should be changed as: 72.3.
======================================================================== If you find our method useful in your research,please consider citing the following papers:
-
H. Song, W. Wang, J. Shen, S. Zhao, and K. M. Lam, Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection, European Conference on Computer Vision, 2018
-
W. Wang, J. Shen, and L. Shao,Video salient object detection via fully convolutional networks,IEEE Trans. on Image Processing, 27(1):38-49, 2018
-
W. Wang, J. Shen, R. Yang, and F. Porikli, Saliency-aware video object segmentation,IEEE Trans. on Pattern Analysis and Machine Intelligence, 40(1):20-33, 2018
========================================================================
Any comments, please email:[email protected]