文献类型：期刊文献

英文题名：Salient object detection of social images based on semantic tag context

作者：Liang, Ye[1,2];Lang, Congyan[1];Yu, Jian[1];Liu, Hongzhe[2]

第一作者：Liang, Ye

通讯作者：Lang, CY[1]

机构：[1]Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing 100044, Peoples R China;[2]Beijing Union Univ, Beijing Key Lab Informat Serv Engn, Beijing 100101, Peoples R China

第一机构：Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing 100044, Peoples R China

通讯机构：[1]corresponding author), Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing 100044, Peoples R China.

年份：2017

卷号：23

期号：4

起止页码：233-247

外文期刊名：INTERNATIONAL JOURNAL OF SENSOR NETWORKS

收录：;EI(收录号：20215011304543);Scopus(收录号：2-s2.0-85017341288);WOS:【SCI-EXPANDED(收录号:WOS:000403578400003)】；

基金：This work was supported in part by the Program project of Beijing Municipal Education Commission (KM 201511417008), open project of Beijing Key Laboratory of Information Service Engineering (Zk20201402), the National Natural Science Foundation of China (Grant No. 62372148), the National Natural Science Foundation of China (Grant No. 61272352) and Beijing Natural Science Foundation (4152016).

语种：英文

外文关键词：saliency; salient object detection; social images; tags

摘要：Salient object detection is an important process for machines to understand visual contents as humans. Typically, most previous studies on salient object detection infer salient map by only using the visual features. In this paper, we propose a new paradigm on salient object detection, which aims at producing more reliable results by mining the context information from user's annotated tags. To address this problem, we firstly construct a large scale salient object dataset, which includes 5429 images from the NUSWIDE dataset (a real world web image database from National University of Singapore) with tag information and accurate human-labeled masks. Moreover, a specialised conditional random field (CRF) model is also proposed which takes account of both tag contexts and appearance cues. Extensive experiments show the effectiveness and superiority of our model which can accurately locate the salient objects.