Salient Object Detection with Higher Order Potentials and Learning Affinity
Salient Object Detection with Higher Order Potentials and Learning Affinity
复制标题
具有高阶势和学习亲和力的显着目标检测
DOI：
10.1109/lsp.2014.2377216
复制
发表时间：
2015-09
影响因子：
3.9
通讯作者：
Yuan Xinzhe
中科院分区：
文献类型：
--
作者：
Zhang Lihe;Yuan Xinzhe
In this paper, we propose a novel graph-based salient object detection algorithm which exploits higher order potential to capture the cross-scale grouping cues instead of using multi-scale graph model or naive multi-scale fusion (i.e. individually compute a saliency result for each scale and then combine them). And, we investigate the importance of graph affinities in graph labeling. We take both local (spatial distribution) and nonlocal (feature distribution) priors into account and learn the pairwise similarity values in a semi-supervised manner, thereby obtaining a faithful graph affinity model. With the guidance of foreground and background seeds, salient object detection is formulated as a labeling inference problem. Extensive experiments on two large benchmark datasets demonstrate the proposed method performs well when against the state-of-the-art methods in terms of accuracy.
登录
查看更多内容
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
DOI：
--
发表时间：
2013
期刊：
--
影响因子：
--
作者：
Ming-Ming Cheng-Ming;N. Mitra;Xiaolei Huang;Philip H. S. Torr;Shimin Hu
通讯作者：
Ming-Ming Cheng-Ming;N. Mitra;Xiaolei Huang;Philip H. S. Torr;Shimin Hu
DOI：
10.1109/34.868688
发表时间：
2000-08-01
影响因子：
23.6
作者：
Shi, JB;Malik, J
通讯作者：
Malik, J
DOI：
10.1109/34.730558
发表时间：
1998-11-01
影响因子：
23.6
作者：
Itti, L;Koch, C;Niebur, E
通讯作者：
Niebur, E
DOI：
10.1109/cvpr.2013.153
发表时间：
2013-06
期刊：
2013 IEEE Conference on Computer Vision and Pattern Recognition
影响因子：
--
作者：
Qiong Yan;Li Xu;Jianping Shi;Jiaya Jia
通讯作者：
Qiong Yan;Li Xu;Jianping Shi;Jiaya Jia