Two-Stage Saliency Detection Based on Continuous CRF and Sparse Coding

摘要：

　　In the state-of-the-art saliency detection methods based on contrast priors,little attention is paid on the region smoothness constraints.The paper proposes a two-stage saliency detection method in which a smoothness prior is explicitly involved in a continuous Conditional Random Field (CRF).In stage one,we construct a continuous CRF based on the sparse codes of perceptual features on all locations,and minimize the energy of CRF to obtain discrimination maps.In stage two,we train a discriminative machine and learn the saliency maps from discrimination maps,aiming to take the human attention priors into consideration.Our experiments on MSRA-1000 show that the new method is effective against the state-of-the-art methods.

关键词： saliency continuous CRF sparse coding

作者: Qiyang Zhao Weibo Li Fan Wang Baolin Yin

作者单位: NLSDE,School of Computer Science and Engineering Beihang University,Beijing,China Beijing Youth Politics College,Beijing,China

会议类型: 国际会议

会议名称: Chinese Conference on Pattern Recognition, CCPR(2014年全国模式识别学术会议)

会议地点: 长沙

会议语种:英文

页码: 455-463

在线出版日期: 2014-11-01（万方平台首次上网日期，不代表论文的发表时间）