http://ice.dlut.edu.cn/lu/publications.html
一个非常牛的实验室,四篇iccv 2017,膜拜!
Pingping Zhang一人两篇!!!
-
Pingping Zhang, Dong Wang, Huchuan Lu,Hongyu Wang, Xiang Ruan, Amulet: Aggregating Multi-Level Convolutional Features for Salient Object Detection,ICCV2017,[PDF][Code]
-
PingPing Zhang, Dong Wang, Huchuan Lu,Hongyu Wang,Baocai Yin,Learning Uncertain Convolutional Features for Accurate Saliency Detection, ICCV2017,[PDF][Code]
-
Tiantian Wang, Ali Borji,Lihe Zhang,Pingping Zhang, Huchuan Lu,A Stagewise Refinement Model for Detecting Salient Objects in Images, ICCV2017,[PDF][Code]
-
Zimo Liu, Dong Wang, Huchuan Lu, Stepwise Metric Promotion for Unsupervised Video Person Re-identification, ICCV2017,[PDF][Code]
其中第二篇分割提到dropout做改进,使用了conv+r-dropout+pooling的结构,此外有The detailed explanation of deconvolution.
第三篇中多阶段,其中使用了The structure of the pyramid pooling module