点击次数：

论文类型：期刊论文

发表时间：2019-03-29

发表刊物：IEEE Transactions on Image Processing

收录刊物：SCI

所属单位：School of communication and information system

关键字：Salient object

摘要：Object proposals are a series of candidate segments
containing the objects of interest, which are taken as preprocessing
and widely applied in various vision tasks. However, most
of existing saliency approaches only utilizes the proposals to compute a location prior. In this paper, we naturally take the proposals as the bags of instances of multiple instances learning (MIL), where the instances are the superpixels contained in the proposals, and formulate saliency detection problem as an MIL task (i.e., predict the labels of instances using the classifier in the MIL framework). This method all