Salient object detection via double random walks with dual restarts

Salient object detection via double random walks with dual restarts
复制标题

通过双重随机游走和双重重启进行显着目标检测

DOI:
10.1016/j.imavis.2019.10.008
复制
发表时间:
2020
影响因子:
4.7
通讯作者:
Wei Guohua
Wei Guohua
中科院分区:
计算机科学3区
文献类型:
--
作者:
Yang Jiaxing;Fang Xiang;Zhang Lihe;Lu Huchuan;Wei Guohua

文献摘要

参考文献

相似文献

在本文中,我们提出了一种基于双重随机游走和双重重启的新颖显着性模型。分别代表前景和背景属性的两个代理(也称为步行者)同时在图上行走以探索显着性分布。首先,我们提出传播距离度量并用它来计算两个智能体的初始分布,而不是使用测地距离。其次,两个智能体从各自的初始分布开始遍历图,然后通过重启机制相互交互来纠正其行进路线,这强制智能体在每次移动后以一定的概率返回到某些特定节点。我们定义双重重启是为了考虑两个代理之间的交互和权重。广泛的评估表明,所提出的算法在四个基准数据集上的性能优于其他最先进的方法。
In this paper, we propose a novel saliency model based on double random walks with dual restarts. Two agents (also known as walkers) respectively representing the foreground and background properties simultaneously walk on a graph to explore saliency distribution. First, we propose the propagation distance measure and use it to calculate the initial distributions of the two agents instead of using geodesic distance. Second, the two agents traverse the graph starting from their own initial distribution, and then interact with each other to correct their travel routes by the restart mechanism, which enforces the agents to return to some specific nodes with a certain probability after every movement. We define the dual restarts to take into account interaction between and weighting of two agents. Extensive evaluations demonstrate that the proposed algorithm performs favorably against other state-of-the-art methods on four benchmark datasets.
DOI: 10.1109/iccv.2015.165
发表时间: 2015-12
期刊: 2015 IEEE International Conference on Computer Vision (ICCV)
影响因子: --
作者:
Jianming Zhang;S. Sclaroff;Zhe L. Lin;Xiaohui Shen;Brian L. Price;R. Mech
通讯作者: Jianming Zhang;S. Sclaroff;Zhe L. Lin;Xiaohui Shen;Brian L. Price;R. Mech
基于多约束特征匹配和跨标签传播的RGBD图像共显着性检测
DOI: 10.1109/tip.2017.2763819
发表时间: 2017-10
期刊: IEEE Transactions on Image
影响因子: --
作者:
Runmin Cong;Jianjun Lei;Huazhu Fu;Qingming Huang;Xiaochun Cao;Chunping Hou
通讯作者: Chunping Hou
DOI: 10.1109/tip.2010.2053940
发表时间: 2010-12
影响因子: 10.6
作者:
Viswanath Gopalakrishnan;Yiqun Hu;D. Rajan
通讯作者: Viswanath Gopalakrishnan;Yiqun Hu;D. Rajan
DOI: --
发表时间: 2017-01
期刊: ArXiv
影响因子: --
作者:
Junting Pan;C. Canton-Ferrer;Kevin McGuinness;N. O’Connor;Jordi Torres;E. Sayrol;Xavier Giro-i-Nieto-Xavier-Giro-i-Nie
通讯作者: Junting Pan;C. Canton-Ferrer;Kevin McGuinness;N. O’Connor;Jordi Torres;E. Sayrol;Xavier Giro-i-Nieto-Xavier-Giro-i-Nie
DOI: 10.1109/tpami.2011.272
发表时间: 2012-10-01
影响因子: 23.6
作者:
Goferman, Stas;Zelnik-Manor, Lihi;Tal, Ayellet
通讯作者: Tal, Ayellet